Hugging Face's logo

umd-vt-nyu
/
JH_dc-vae-f32c32-sana-1.0-768_patch-1_baseline_fusion

Safetensors
Model card Files
xet
Community
jiuhai commited on
Commit
97d3611
·
verified ·
1 Parent(s): a615920

Upload folder using huggingface_hub

Browse files
Files changed (35) hide show
  1. .gitattributes +2 -0
  2. checkpoint-269000/config.json +79 -0
  3. checkpoint-269000/generation_config.json +6 -0
  4. checkpoint-269000/model-00001-of-00002.safetensors +3 -0
  5. checkpoint-269000/model-00002-of-00002.safetensors +3 -0
  6. checkpoint-269000/model.safetensors.index.json +1167 -0
  7. checkpoint-269000/optimizer.pt +3 -0
  8. checkpoint-269000/rng_state_0.pth +3 -0
  9. checkpoint-269000/rng_state_1.pth +3 -0
  10. checkpoint-269000/rng_state_2.pth +3 -0
  11. checkpoint-269000/rng_state_3.pth +3 -0
  12. checkpoint-269000/rng_state_4.pth +3 -0
  13. checkpoint-269000/rng_state_5.pth +3 -0
  14. checkpoint-269000/rng_state_6.pth +3 -0
  15. checkpoint-269000/rng_state_7.pth +3 -0
  16. checkpoint-269000/scheduler.pt +3 -0
  17. checkpoint-269000/trainer_state.json +3 -0
  18. checkpoint-269000/training_args.bin +3 -0
  19. checkpoint-270000/config.json +79 -0
  20. checkpoint-270000/generation_config.json +6 -0
  21. checkpoint-270000/model-00001-of-00002.safetensors +3 -0
  22. checkpoint-270000/model-00002-of-00002.safetensors +3 -0
  23. checkpoint-270000/model.safetensors.index.json +1167 -0
  24. checkpoint-270000/optimizer.pt +3 -0
  25. checkpoint-270000/rng_state_0.pth +3 -0
  26. checkpoint-270000/rng_state_1.pth +3 -0
  27. checkpoint-270000/rng_state_2.pth +3 -0
  28. checkpoint-270000/rng_state_3.pth +3 -0
  29. checkpoint-270000/rng_state_4.pth +3 -0
  30. checkpoint-270000/rng_state_5.pth +3 -0
  31. checkpoint-270000/rng_state_6.pth +3 -0
  32. checkpoint-270000/rng_state_7.pth +3 -0
  33. checkpoint-270000/scheduler.pt +3 -0
  34. checkpoint-270000/trainer_state.json +3 -0
  35. checkpoint-270000/training_args.bin +3 -0
.gitattributes CHANGED
@@ -86,3 +86,5 @@ checkpoint-249000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
86
  checkpoint-250000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
87
  checkpoint-259000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
88
  checkpoint-260000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
 
 
 
86
  checkpoint-250000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
87
  checkpoint-259000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
88
  checkpoint-260000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
89
+ checkpoint-269000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
90
+ checkpoint-270000/trainer_state.json filter=lfs diff=lfs merge=lfs -text
checkpoint-269000/config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ar_steps": 1,
3
+ "architectures": [
4
+ "DiffVLMBaseline"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "condition_layer": -1,
9
+ "eos_token_id": 151645,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1536,
12
+ "image_token_id": 151655,
13
+ "img_cross_attention_dim": 2048,
14
+ "img_diffuser_depth": 1,
15
+ "img_ffn_dim_multiplier": null,
16
+ "img_hidden_size": 1536,
17
+ "img_multiple_of": 256,
18
+ "img_norm_eps": 1e-05,
19
+ "img_num_attention_heads": 12,
20
+ "img_num_kv_heads": 12,
21
+ "img_qk_norm": true,
22
+ "in_channels": 32,
23
+ "initializer_range": 0.02,
24
+ "inject_img_diffuser": false,
25
+ "input_size": 32,
26
+ "intermediate_size": 8960,
27
+ "layer_group_size": 7,
28
+ "layerwise_start_idx": 0,
29
+ "lora_alpha": 16,
30
+ "lora_bias": "none",
31
+ "lora_dropout": 0.05,
32
+ "lora_enable": false,
33
+ "lora_r": 64,
34
+ "max_position_embeddings": 32768,
35
+ "max_window_layers": 28,
36
+ "model_type": "qwen2_vl",
37
+ "non_linearity": 1,
38
+ "norm_elementwise_affine": true,
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 28,
41
+ "num_key_value_heads": 2,
42
+ "patch_size": 1,
43
+ "repa_coeff": 0.5,
44
+ "repa_layers": null,
45
+ "repa_shared": false,
46
+ "rms_norm_eps": 1e-06,
47
+ "rope_scaling": {
48
+ "mrope_section": [
49
+ 16,
50
+ 24,
51
+ 24
52
+ ],
53
+ "rope_type": "default",
54
+ "type": "default"
55
+ },
56
+ "rope_theta": 1000000.0,
57
+ "sample_size": 128,
58
+ "sampling_steps": 28,
59
+ "sliding_window": null,
60
+ "tie_word_embeddings": true,
61
+ "torch_dtype": "bfloat16",
62
+ "transformers_version": "4.47.0",
63
+ "use_cache": true,
64
+ "use_repa": false,
65
+ "use_residual_attn": false,
66
+ "use_sliding_window": false,
67
+ "vae_path": "mit-han-lab/dc-ae-f32c32-in-1.0-diffusers",
68
+ "video_token_id": 151656,
69
+ "vision_config": {
70
+ "hidden_size": 1536,
71
+ "in_chans": 3,
72
+ "model_type": "qwen2_vl",
73
+ "spatial_patch_size": 14
74
+ },
75
+ "vision_end_token_id": 151653,
76
+ "vision_start_token_id": 151652,
77
+ "vision_token_id": 151654,
78
+ "vocab_size": 151936
79
+ }
checkpoint-269000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.47.0"
6
+ }
checkpoint-269000/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a37decebc5600d04bba942b02d226820299c6a1a4d4aa38c36f0cde36276a3
3
+ size 4980624888
checkpoint-269000/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd907a633856fc36eb1747af07efc380330e6f2ca7c2cebdfad214afd8452b5
3
+ size 1918602176
checkpoint-269000/model.safetensors.index.json ADDED
@@ -0,0 +1,1167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6899096400
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "img2text.bias": "model-00001-of-00002.safetensors",
8
+ "img2text.weight": "model-00001-of-00002.safetensors",
9
+ "img_norm_out.linear_1.bias": "model-00001-of-00002.safetensors",
10
+ "img_norm_out.linear_1.weight": "model-00001-of-00002.safetensors",
11
+ "img_norm_out.linear_2.bias": "model-00001-of-00002.safetensors",
12
+ "img_norm_out.linear_2.weight": "model-00001-of-00002.safetensors",
13
+ "layers.0.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
14
+ "layers.0.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
15
+ "layers.0.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
16
+ "layers.0.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
17
+ "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
23
+ "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
24
+ "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
26
+ "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
27
+ "layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
28
+ "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
29
+ "layers.1.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
30
+ "layers.1.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
31
+ "layers.1.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
32
+ "layers.1.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
33
+ "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
35
+ "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
36
+ "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
37
+ "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
39
+ "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
42
+ "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
44
+ "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
45
+ "layers.10.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
46
+ "layers.10.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
47
+ "layers.10.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
48
+ "layers.10.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
49
+ "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
51
+ "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
52
+ "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
53
+ "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
55
+ "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
56
+ "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
57
+ "layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
58
+ "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
59
+ "layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
60
+ "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "layers.11.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
62
+ "layers.11.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
63
+ "layers.11.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
64
+ "layers.11.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
65
+ "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
67
+ "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
68
+ "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
69
+ "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
71
+ "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
72
+ "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
73
+ "layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
74
+ "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
75
+ "layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
76
+ "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
77
+ "layers.12.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
78
+ "layers.12.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
79
+ "layers.12.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
80
+ "layers.12.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
81
+ "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
83
+ "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
84
+ "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
87
+ "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
88
+ "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
89
+ "layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
90
+ "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
91
+ "layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
92
+ "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
93
+ "layers.13.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
94
+ "layers.13.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
95
+ "layers.13.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
96
+ "layers.13.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
97
+ "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
103
+ "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
106
+ "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
108
+ "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
109
+ "layers.14.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
110
+ "layers.14.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
111
+ "layers.14.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
112
+ "layers.14.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
113
+ "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
114
+ "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
115
+ "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
116
+ "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
117
+ "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
119
+ "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
120
+ "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
121
+ "layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
122
+ "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
124
+ "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "layers.15.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
126
+ "layers.15.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
127
+ "layers.15.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
128
+ "layers.15.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
129
+ "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
135
+ "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
138
+ "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
140
+ "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "layers.16.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
142
+ "layers.16.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
143
+ "layers.16.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
144
+ "layers.16.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
145
+ "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
147
+ "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
148
+ "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
149
+ "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
+ "layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
151
+ "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
152
+ "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
153
+ "layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
154
+ "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
155
+ "layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
156
+ "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
157
+ "layers.17.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
158
+ "layers.17.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
159
+ "layers.17.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
160
+ "layers.17.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
161
+ "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
163
+ "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
164
+ "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
165
+ "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
167
+ "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
168
+ "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
170
+ "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
171
+ "layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
172
+ "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
173
+ "layers.18.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
174
+ "layers.18.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
175
+ "layers.18.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
176
+ "layers.18.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
177
+ "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
178
+ "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
179
+ "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
180
+ "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
181
+ "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
183
+ "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
184
+ "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
185
+ "layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
186
+ "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
188
+ "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
189
+ "layers.19.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
190
+ "layers.19.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
191
+ "layers.19.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
192
+ "layers.19.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
193
+ "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
195
+ "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
196
+ "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
197
+ "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
199
+ "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
200
+ "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
201
+ "layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
202
+ "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
203
+ "layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
204
+ "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "layers.2.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
206
+ "layers.2.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
207
+ "layers.2.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
208
+ "layers.2.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
209
+ "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
210
+ "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
211
+ "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
212
+ "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
213
+ "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
214
+ "layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
215
+ "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
216
+ "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
217
+ "layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
218
+ "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
219
+ "layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
220
+ "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "layers.20.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
222
+ "layers.20.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
223
+ "layers.20.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
224
+ "layers.20.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
225
+ "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
226
+ "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
227
+ "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
228
+ "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
229
+ "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
230
+ "layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
231
+ "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
232
+ "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
233
+ "layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
234
+ "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
235
+ "layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
236
+ "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
237
+ "layers.21.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
238
+ "layers.21.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
239
+ "layers.21.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
240
+ "layers.21.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
241
+ "layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
243
+ "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
244
+ "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
+ "layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
247
+ "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
250
+ "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
251
+ "layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
252
+ "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
253
+ "layers.22.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
254
+ "layers.22.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
255
+ "layers.22.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
256
+ "layers.22.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
257
+ "layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
258
+ "layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
259
+ "layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
260
+ "layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
261
+ "layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
263
+ "layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
264
+ "layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
265
+ "layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
266
+ "layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
267
+ "layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
268
+ "layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
+ "layers.23.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
270
+ "layers.23.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
271
+ "layers.23.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
272
+ "layers.23.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
273
+ "layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
275
+ "layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
276
+ "layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
277
+ "layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
279
+ "layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
281
+ "layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
282
+ "layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
284
+ "layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
285
+ "layers.24.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
286
+ "layers.24.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
287
+ "layers.24.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
288
+ "layers.24.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
289
+ "layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
290
+ "layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
291
+ "layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
292
+ "layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
293
+ "layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
294
+ "layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
295
+ "layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
296
+ "layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
297
+ "layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
298
+ "layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
299
+ "layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
300
+ "layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
301
+ "layers.25.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
302
+ "layers.25.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
303
+ "layers.25.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
304
+ "layers.25.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
305
+ "layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
306
+ "layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
307
+ "layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
308
+ "layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
309
+ "layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
310
+ "layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
311
+ "layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
312
+ "layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
313
+ "layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
314
+ "layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
315
+ "layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
316
+ "layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
317
+ "layers.26.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
318
+ "layers.26.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
319
+ "layers.26.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
320
+ "layers.26.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
321
+ "layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
322
+ "layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
323
+ "layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
324
+ "layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
325
+ "layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
326
+ "layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
327
+ "layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
328
+ "layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
329
+ "layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
330
+ "layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
+ "layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
332
+ "layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "layers.27.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
334
+ "layers.27.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
335
+ "layers.27.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
336
+ "layers.27.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
337
+ "layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
338
+ "layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
339
+ "layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
340
+ "layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
341
+ "layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
342
+ "layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
343
+ "layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
344
+ "layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
345
+ "layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
346
+ "layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
347
+ "layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
348
+ "layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
+ "layers.3.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
350
+ "layers.3.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
351
+ "layers.3.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
352
+ "layers.3.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
353
+ "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
354
+ "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
355
+ "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
356
+ "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
357
+ "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
358
+ "layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
359
+ "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
360
+ "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
361
+ "layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
362
+ "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
363
+ "layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
364
+ "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
365
+ "layers.4.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
366
+ "layers.4.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
367
+ "layers.4.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
368
+ "layers.4.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
369
+ "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
370
+ "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
371
+ "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
372
+ "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
373
+ "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
374
+ "layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
375
+ "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
376
+ "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
377
+ "layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
378
+ "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
379
+ "layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
380
+ "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
381
+ "layers.5.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
382
+ "layers.5.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
383
+ "layers.5.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
384
+ "layers.5.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
385
+ "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
386
+ "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
387
+ "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
388
+ "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
389
+ "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
390
+ "layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
391
+ "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
392
+ "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
393
+ "layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
394
+ "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
395
+ "layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
396
+ "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
397
+ "layers.6.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
398
+ "layers.6.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
399
+ "layers.6.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
400
+ "layers.6.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
401
+ "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
402
+ "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
403
+ "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
404
+ "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
405
+ "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
406
+ "layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
407
+ "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
408
+ "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
409
+ "layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
410
+ "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
411
+ "layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
412
+ "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
413
+ "layers.7.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
414
+ "layers.7.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
415
+ "layers.7.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
416
+ "layers.7.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
417
+ "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
418
+ "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
419
+ "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
420
+ "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
421
+ "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
422
+ "layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
423
+ "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
424
+ "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
425
+ "layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
426
+ "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
427
+ "layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
428
+ "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
429
+ "layers.8.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
430
+ "layers.8.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
431
+ "layers.8.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
432
+ "layers.8.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
433
+ "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
434
+ "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
435
+ "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
436
+ "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
437
+ "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
438
+ "layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
439
+ "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
440
+ "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
441
+ "layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
442
+ "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
443
+ "layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
444
+ "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
445
+ "layers.9.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
446
+ "layers.9.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
447
+ "layers.9.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
448
+ "layers.9.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
449
+ "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
450
+ "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
451
+ "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
452
+ "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
453
+ "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
454
+ "layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
455
+ "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
456
+ "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
457
+ "layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
458
+ "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
459
+ "layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
460
+ "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
461
+ "norm.weight": "model-00002-of-00002.safetensors",
462
+ "patch_embedder.proj.bias": "model-00001-of-00002.safetensors",
463
+ "patch_embedder.proj.weight": "model-00001-of-00002.safetensors",
464
+ "t_embedder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors",
465
+ "t_embedder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors",
466
+ "t_embedder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors",
467
+ "t_embedder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors",
468
+ "txt_layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
469
+ "txt_layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
470
+ "txt_layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
471
+ "txt_layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
472
+ "txt_layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
473
+ "txt_layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
474
+ "txt_layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
475
+ "txt_layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
476
+ "txt_layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
477
+ "txt_layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
478
+ "txt_layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
479
+ "txt_layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
480
+ "txt_layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
481
+ "txt_layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
482
+ "txt_layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
483
+ "txt_layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
484
+ "txt_layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
485
+ "txt_layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
486
+ "txt_layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
487
+ "txt_layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
488
+ "txt_layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
489
+ "txt_layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
490
+ "txt_layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
491
+ "txt_layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
492
+ "txt_layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
493
+ "txt_layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
494
+ "txt_layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
495
+ "txt_layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
496
+ "txt_layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
497
+ "txt_layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
498
+ "txt_layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
499
+ "txt_layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
500
+ "txt_layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
501
+ "txt_layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
502
+ "txt_layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
503
+ "txt_layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
504
+ "txt_layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
505
+ "txt_layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
506
+ "txt_layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
507
+ "txt_layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
508
+ "txt_layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
509
+ "txt_layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
510
+ "txt_layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
511
+ "txt_layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
512
+ "txt_layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
513
+ "txt_layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
514
+ "txt_layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
515
+ "txt_layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
516
+ "txt_layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
517
+ "txt_layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
518
+ "txt_layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
519
+ "txt_layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
520
+ "txt_layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
521
+ "txt_layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
522
+ "txt_layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
523
+ "txt_layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
524
+ "txt_layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
525
+ "txt_layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
526
+ "txt_layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
527
+ "txt_layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
528
+ "txt_layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
529
+ "txt_layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
530
+ "txt_layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
531
+ "txt_layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
532
+ "txt_layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
533
+ "txt_layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
534
+ "txt_layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
535
+ "txt_layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
536
+ "txt_layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
537
+ "txt_layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
538
+ "txt_layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
539
+ "txt_layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
540
+ "txt_layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
541
+ "txt_layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
542
+ "txt_layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
543
+ "txt_layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
544
+ "txt_layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
545
+ "txt_layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
546
+ "txt_layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
547
+ "txt_layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
548
+ "txt_layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
549
+ "txt_layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
550
+ "txt_layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
551
+ "txt_layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
552
+ "txt_layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
553
+ "txt_layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
554
+ "txt_layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
555
+ "txt_layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
556
+ "txt_layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
557
+ "txt_layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
558
+ "txt_layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
559
+ "txt_layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
560
+ "txt_layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
561
+ "txt_layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
562
+ "txt_layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
563
+ "txt_layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
564
+ "txt_layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
565
+ "txt_layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
566
+ "txt_layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
567
+ "txt_layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
568
+ "txt_layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
569
+ "txt_layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
570
+ "txt_layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
571
+ "txt_layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
572
+ "txt_layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
573
+ "txt_layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
574
+ "txt_layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
575
+ "txt_layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
576
+ "txt_layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
577
+ "txt_layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
578
+ "txt_layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
579
+ "txt_layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
580
+ "txt_layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
581
+ "txt_layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
582
+ "txt_layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
583
+ "txt_layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
584
+ "txt_layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
585
+ "txt_layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
586
+ "txt_layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
587
+ "txt_layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
588
+ "txt_layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
589
+ "txt_layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
590
+ "txt_layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
591
+ "txt_layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
592
+ "txt_layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
593
+ "txt_layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
594
+ "txt_layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
595
+ "txt_layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
596
+ "txt_layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
597
+ "txt_layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
598
+ "txt_layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
599
+ "txt_layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
600
+ "txt_layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
601
+ "txt_layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
602
+ "txt_layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
603
+ "txt_layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
604
+ "txt_layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
605
+ "txt_layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
606
+ "txt_layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
607
+ "txt_layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
608
+ "txt_layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
609
+ "txt_layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
610
+ "txt_layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
611
+ "txt_layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
612
+ "txt_layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
613
+ "txt_layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
614
+ "txt_layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
615
+ "txt_layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
616
+ "txt_layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
617
+ "txt_layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
618
+ "txt_layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
619
+ "txt_layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
620
+ "txt_layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
621
+ "txt_layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
622
+ "txt_layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
623
+ "txt_layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
624
+ "txt_layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
625
+ "txt_layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
626
+ "txt_layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
627
+ "txt_layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
628
+ "txt_layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
629
+ "txt_layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
630
+ "txt_layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
631
+ "txt_layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
632
+ "txt_layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
633
+ "txt_layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
634
+ "txt_layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
635
+ "txt_layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
636
+ "txt_layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
637
+ "txt_layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
638
+ "txt_layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
639
+ "txt_layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
640
+ "txt_layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
641
+ "txt_layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
642
+ "txt_layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
643
+ "txt_layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
644
+ "txt_layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
645
+ "txt_layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
646
+ "txt_layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
647
+ "txt_layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
648
+ "txt_layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
649
+ "txt_layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
650
+ "txt_layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
651
+ "txt_layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
652
+ "txt_layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
653
+ "txt_layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
654
+ "txt_layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
655
+ "txt_layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
656
+ "txt_layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
657
+ "txt_layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
658
+ "txt_layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
659
+ "txt_layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
660
+ "txt_layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
661
+ "txt_layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
662
+ "txt_layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
663
+ "txt_layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
664
+ "txt_layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
665
+ "txt_layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
666
+ "txt_layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
667
+ "txt_layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
668
+ "txt_layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
669
+ "txt_layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
670
+ "txt_layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
671
+ "txt_layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
672
+ "txt_layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
673
+ "txt_layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
674
+ "txt_layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
675
+ "txt_layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
676
+ "txt_layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
677
+ "txt_layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
678
+ "txt_layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
679
+ "txt_layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
680
+ "txt_layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
681
+ "txt_layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
682
+ "txt_layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
683
+ "txt_layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
684
+ "txt_layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
685
+ "txt_layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
686
+ "txt_layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
687
+ "txt_layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
688
+ "txt_layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
689
+ "txt_layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
690
+ "txt_layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
691
+ "txt_layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
692
+ "txt_layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
693
+ "txt_layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
694
+ "txt_layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
695
+ "txt_layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
696
+ "txt_layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
697
+ "txt_layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
698
+ "txt_layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
699
+ "txt_layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
700
+ "txt_layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
701
+ "txt_layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
702
+ "txt_layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
703
+ "txt_layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
704
+ "txt_layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
705
+ "txt_layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
706
+ "txt_layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
707
+ "txt_layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
708
+ "txt_layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
709
+ "txt_layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
710
+ "txt_layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
711
+ "txt_layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
712
+ "txt_layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
713
+ "txt_layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
714
+ "txt_layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
715
+ "txt_layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
716
+ "txt_layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
717
+ "txt_layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
718
+ "txt_layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
719
+ "txt_layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
720
+ "txt_layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
721
+ "txt_layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
722
+ "txt_layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
723
+ "txt_layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
724
+ "txt_layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
725
+ "txt_layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
726
+ "txt_layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
727
+ "txt_layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
728
+ "txt_layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
729
+ "txt_layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
730
+ "txt_layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
731
+ "txt_layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
732
+ "txt_layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
733
+ "txt_layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
734
+ "txt_layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
735
+ "txt_layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
736
+ "txt_layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
737
+ "txt_layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
738
+ "txt_layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
739
+ "txt_layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
740
+ "txt_layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
741
+ "txt_layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
742
+ "txt_layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
743
+ "txt_layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
744
+ "txt_layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
745
+ "txt_layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
746
+ "txt_layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
747
+ "txt_layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
748
+ "txt_layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
749
+ "txt_layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
750
+ "txt_layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
751
+ "txt_layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
752
+ "txt_layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
753
+ "txt_layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
754
+ "txt_layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
755
+ "txt_layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
756
+ "txt_layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
757
+ "txt_layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
758
+ "txt_layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
759
+ "txt_layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
760
+ "txt_layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
761
+ "txt_layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
762
+ "txt_layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
763
+ "txt_layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
764
+ "txt_layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
765
+ "txt_layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
766
+ "txt_layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
767
+ "txt_layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
768
+ "txt_layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
769
+ "txt_layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
770
+ "txt_layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
771
+ "txt_layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
772
+ "txt_layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
773
+ "txt_layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
774
+ "txt_layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
775
+ "txt_layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
776
+ "txt_layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
777
+ "txt_layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
778
+ "txt_layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
779
+ "txt_layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
780
+ "txt_layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
781
+ "txt_layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
782
+ "txt_layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
783
+ "txt_layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
784
+ "txt_layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
785
+ "txt_layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
786
+ "txt_layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
787
+ "txt_layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
788
+ "txt_layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
789
+ "txt_layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
790
+ "txt_layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
791
+ "txt_layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
792
+ "txt_layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
793
+ "txt_layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
794
+ "txt_layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
795
+ "txt_layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
796
+ "txt_layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
797
+ "txt_layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
798
+ "txt_layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
799
+ "txt_layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
800
+ "txt_layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
801
+ "txt_layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
802
+ "txt_layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
803
+ "txt_layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
804
+ "vae.decoder.conv_in.bias": "model-00002-of-00002.safetensors",
805
+ "vae.decoder.conv_in.weight": "model-00002-of-00002.safetensors",
806
+ "vae.decoder.conv_out.conv.bias": "model-00002-of-00002.safetensors",
807
+ "vae.decoder.conv_out.conv.weight": "model-00002-of-00002.safetensors",
808
+ "vae.decoder.norm_out.bias": "model-00002-of-00002.safetensors",
809
+ "vae.decoder.norm_out.weight": "model-00002-of-00002.safetensors",
810
+ "vae.decoder.up_blocks.1.0.conv.bias": "model-00002-of-00002.safetensors",
811
+ "vae.decoder.up_blocks.1.0.conv.weight": "model-00002-of-00002.safetensors",
812
+ "vae.decoder.up_blocks.1.1.conv1.bias": "model-00002-of-00002.safetensors",
813
+ "vae.decoder.up_blocks.1.1.conv1.weight": "model-00002-of-00002.safetensors",
814
+ "vae.decoder.up_blocks.1.1.conv2.weight": "model-00002-of-00002.safetensors",
815
+ "vae.decoder.up_blocks.1.1.norm.bias": "model-00002-of-00002.safetensors",
816
+ "vae.decoder.up_blocks.1.1.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
817
+ "vae.decoder.up_blocks.1.1.norm.running_mean": "model-00002-of-00002.safetensors",
818
+ "vae.decoder.up_blocks.1.1.norm.running_var": "model-00002-of-00002.safetensors",
819
+ "vae.decoder.up_blocks.1.1.norm.weight": "model-00002-of-00002.safetensors",
820
+ "vae.decoder.up_blocks.1.2.conv1.bias": "model-00002-of-00002.safetensors",
821
+ "vae.decoder.up_blocks.1.2.conv1.weight": "model-00002-of-00002.safetensors",
822
+ "vae.decoder.up_blocks.1.2.conv2.weight": "model-00002-of-00002.safetensors",
823
+ "vae.decoder.up_blocks.1.2.norm.bias": "model-00002-of-00002.safetensors",
824
+ "vae.decoder.up_blocks.1.2.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
825
+ "vae.decoder.up_blocks.1.2.norm.running_mean": "model-00002-of-00002.safetensors",
826
+ "vae.decoder.up_blocks.1.2.norm.running_var": "model-00002-of-00002.safetensors",
827
+ "vae.decoder.up_blocks.1.2.norm.weight": "model-00002-of-00002.safetensors",
828
+ "vae.decoder.up_blocks.1.3.conv1.bias": "model-00002-of-00002.safetensors",
829
+ "vae.decoder.up_blocks.1.3.conv1.weight": "model-00002-of-00002.safetensors",
830
+ "vae.decoder.up_blocks.1.3.conv2.weight": "model-00002-of-00002.safetensors",
831
+ "vae.decoder.up_blocks.1.3.norm.bias": "model-00002-of-00002.safetensors",
832
+ "vae.decoder.up_blocks.1.3.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
833
+ "vae.decoder.up_blocks.1.3.norm.running_mean": "model-00002-of-00002.safetensors",
834
+ "vae.decoder.up_blocks.1.3.norm.running_var": "model-00002-of-00002.safetensors",
835
+ "vae.decoder.up_blocks.1.3.norm.weight": "model-00002-of-00002.safetensors",
836
+ "vae.decoder.up_blocks.1.4.conv1.bias": "model-00002-of-00002.safetensors",
837
+ "vae.decoder.up_blocks.1.4.conv1.weight": "model-00002-of-00002.safetensors",
838
+ "vae.decoder.up_blocks.1.4.conv2.weight": "model-00002-of-00002.safetensors",
839
+ "vae.decoder.up_blocks.1.4.norm.bias": "model-00002-of-00002.safetensors",
840
+ "vae.decoder.up_blocks.1.4.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
841
+ "vae.decoder.up_blocks.1.4.norm.running_mean": "model-00002-of-00002.safetensors",
842
+ "vae.decoder.up_blocks.1.4.norm.running_var": "model-00002-of-00002.safetensors",
843
+ "vae.decoder.up_blocks.1.4.norm.weight": "model-00002-of-00002.safetensors",
844
+ "vae.decoder.up_blocks.1.5.conv1.bias": "model-00002-of-00002.safetensors",
845
+ "vae.decoder.up_blocks.1.5.conv1.weight": "model-00002-of-00002.safetensors",
846
+ "vae.decoder.up_blocks.1.5.conv2.weight": "model-00002-of-00002.safetensors",
847
+ "vae.decoder.up_blocks.1.5.norm.bias": "model-00002-of-00002.safetensors",
848
+ "vae.decoder.up_blocks.1.5.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
849
+ "vae.decoder.up_blocks.1.5.norm.running_mean": "model-00002-of-00002.safetensors",
850
+ "vae.decoder.up_blocks.1.5.norm.running_var": "model-00002-of-00002.safetensors",
851
+ "vae.decoder.up_blocks.1.5.norm.weight": "model-00002-of-00002.safetensors",
852
+ "vae.decoder.up_blocks.2.0.conv.bias": "model-00002-of-00002.safetensors",
853
+ "vae.decoder.up_blocks.2.0.conv.weight": "model-00002-of-00002.safetensors",
854
+ "vae.decoder.up_blocks.2.1.conv1.bias": "model-00002-of-00002.safetensors",
855
+ "vae.decoder.up_blocks.2.1.conv1.weight": "model-00002-of-00002.safetensors",
856
+ "vae.decoder.up_blocks.2.1.conv2.weight": "model-00002-of-00002.safetensors",
857
+ "vae.decoder.up_blocks.2.1.norm.bias": "model-00002-of-00002.safetensors",
858
+ "vae.decoder.up_blocks.2.1.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
859
+ "vae.decoder.up_blocks.2.1.norm.running_mean": "model-00002-of-00002.safetensors",
860
+ "vae.decoder.up_blocks.2.1.norm.running_var": "model-00002-of-00002.safetensors",
861
+ "vae.decoder.up_blocks.2.1.norm.weight": "model-00002-of-00002.safetensors",
862
+ "vae.decoder.up_blocks.2.10.conv1.bias": "model-00002-of-00002.safetensors",
863
+ "vae.decoder.up_blocks.2.10.conv1.weight": "model-00002-of-00002.safetensors",
864
+ "vae.decoder.up_blocks.2.10.conv2.weight": "model-00002-of-00002.safetensors",
865
+ "vae.decoder.up_blocks.2.10.norm.bias": "model-00002-of-00002.safetensors",
866
+ "vae.decoder.up_blocks.2.10.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
867
+ "vae.decoder.up_blocks.2.10.norm.running_mean": "model-00002-of-00002.safetensors",
868
+ "vae.decoder.up_blocks.2.10.norm.running_var": "model-00002-of-00002.safetensors",
869
+ "vae.decoder.up_blocks.2.10.norm.weight": "model-00002-of-00002.safetensors",
870
+ "vae.decoder.up_blocks.2.2.conv1.bias": "model-00002-of-00002.safetensors",
871
+ "vae.decoder.up_blocks.2.2.conv1.weight": "model-00002-of-00002.safetensors",
872
+ "vae.decoder.up_blocks.2.2.conv2.weight": "model-00002-of-00002.safetensors",
873
+ "vae.decoder.up_blocks.2.2.norm.bias": "model-00002-of-00002.safetensors",
874
+ "vae.decoder.up_blocks.2.2.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
875
+ "vae.decoder.up_blocks.2.2.norm.running_mean": "model-00002-of-00002.safetensors",
876
+ "vae.decoder.up_blocks.2.2.norm.running_var": "model-00002-of-00002.safetensors",
877
+ "vae.decoder.up_blocks.2.2.norm.weight": "model-00002-of-00002.safetensors",
878
+ "vae.decoder.up_blocks.2.3.conv1.bias": "model-00002-of-00002.safetensors",
879
+ "vae.decoder.up_blocks.2.3.conv1.weight": "model-00002-of-00002.safetensors",
880
+ "vae.decoder.up_blocks.2.3.conv2.weight": "model-00002-of-00002.safetensors",
881
+ "vae.decoder.up_blocks.2.3.norm.bias": "model-00002-of-00002.safetensors",
882
+ "vae.decoder.up_blocks.2.3.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
883
+ "vae.decoder.up_blocks.2.3.norm.running_mean": "model-00002-of-00002.safetensors",
884
+ "vae.decoder.up_blocks.2.3.norm.running_var": "model-00002-of-00002.safetensors",
885
+ "vae.decoder.up_blocks.2.3.norm.weight": "model-00002-of-00002.safetensors",
886
+ "vae.decoder.up_blocks.2.4.conv1.bias": "model-00002-of-00002.safetensors",
887
+ "vae.decoder.up_blocks.2.4.conv1.weight": "model-00002-of-00002.safetensors",
888
+ "vae.decoder.up_blocks.2.4.conv2.weight": "model-00002-of-00002.safetensors",
889
+ "vae.decoder.up_blocks.2.4.norm.bias": "model-00002-of-00002.safetensors",
890
+ "vae.decoder.up_blocks.2.4.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
891
+ "vae.decoder.up_blocks.2.4.norm.running_mean": "model-00002-of-00002.safetensors",
892
+ "vae.decoder.up_blocks.2.4.norm.running_var": "model-00002-of-00002.safetensors",
893
+ "vae.decoder.up_blocks.2.4.norm.weight": "model-00002-of-00002.safetensors",
894
+ "vae.decoder.up_blocks.2.5.conv1.bias": "model-00002-of-00002.safetensors",
895
+ "vae.decoder.up_blocks.2.5.conv1.weight": "model-00002-of-00002.safetensors",
896
+ "vae.decoder.up_blocks.2.5.conv2.weight": "model-00002-of-00002.safetensors",
897
+ "vae.decoder.up_blocks.2.5.norm.bias": "model-00002-of-00002.safetensors",
898
+ "vae.decoder.up_blocks.2.5.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
899
+ "vae.decoder.up_blocks.2.5.norm.running_mean": "model-00002-of-00002.safetensors",
900
+ "vae.decoder.up_blocks.2.5.norm.running_var": "model-00002-of-00002.safetensors",
901
+ "vae.decoder.up_blocks.2.5.norm.weight": "model-00002-of-00002.safetensors",
902
+ "vae.decoder.up_blocks.2.6.conv1.bias": "model-00002-of-00002.safetensors",
903
+ "vae.decoder.up_blocks.2.6.conv1.weight": "model-00002-of-00002.safetensors",
904
+ "vae.decoder.up_blocks.2.6.conv2.weight": "model-00002-of-00002.safetensors",
905
+ "vae.decoder.up_blocks.2.6.norm.bias": "model-00002-of-00002.safetensors",
906
+ "vae.decoder.up_blocks.2.6.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
907
+ "vae.decoder.up_blocks.2.6.norm.running_mean": "model-00002-of-00002.safetensors",
908
+ "vae.decoder.up_blocks.2.6.norm.running_var": "model-00002-of-00002.safetensors",
909
+ "vae.decoder.up_blocks.2.6.norm.weight": "model-00002-of-00002.safetensors",
910
+ "vae.decoder.up_blocks.2.7.conv1.bias": "model-00002-of-00002.safetensors",
911
+ "vae.decoder.up_blocks.2.7.conv1.weight": "model-00002-of-00002.safetensors",
912
+ "vae.decoder.up_blocks.2.7.conv2.weight": "model-00002-of-00002.safetensors",
913
+ "vae.decoder.up_blocks.2.7.norm.bias": "model-00002-of-00002.safetensors",
914
+ "vae.decoder.up_blocks.2.7.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
915
+ "vae.decoder.up_blocks.2.7.norm.running_mean": "model-00002-of-00002.safetensors",
916
+ "vae.decoder.up_blocks.2.7.norm.running_var": "model-00002-of-00002.safetensors",
917
+ "vae.decoder.up_blocks.2.7.norm.weight": "model-00002-of-00002.safetensors",
918
+ "vae.decoder.up_blocks.2.8.conv1.bias": "model-00002-of-00002.safetensors",
919
+ "vae.decoder.up_blocks.2.8.conv1.weight": "model-00002-of-00002.safetensors",
920
+ "vae.decoder.up_blocks.2.8.conv2.weight": "model-00002-of-00002.safetensors",
921
+ "vae.decoder.up_blocks.2.8.norm.bias": "model-00002-of-00002.safetensors",
922
+ "vae.decoder.up_blocks.2.8.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
923
+ "vae.decoder.up_blocks.2.8.norm.running_mean": "model-00002-of-00002.safetensors",
924
+ "vae.decoder.up_blocks.2.8.norm.running_var": "model-00002-of-00002.safetensors",
925
+ "vae.decoder.up_blocks.2.8.norm.weight": "model-00002-of-00002.safetensors",
926
+ "vae.decoder.up_blocks.2.9.conv1.bias": "model-00002-of-00002.safetensors",
927
+ "vae.decoder.up_blocks.2.9.conv1.weight": "model-00002-of-00002.safetensors",
928
+ "vae.decoder.up_blocks.2.9.conv2.weight": "model-00002-of-00002.safetensors",
929
+ "vae.decoder.up_blocks.2.9.norm.bias": "model-00002-of-00002.safetensors",
930
+ "vae.decoder.up_blocks.2.9.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
931
+ "vae.decoder.up_blocks.2.9.norm.running_mean": "model-00002-of-00002.safetensors",
932
+ "vae.decoder.up_blocks.2.9.norm.running_var": "model-00002-of-00002.safetensors",
933
+ "vae.decoder.up_blocks.2.9.norm.weight": "model-00002-of-00002.safetensors",
934
+ "vae.decoder.up_blocks.3.0.conv.bias": "model-00002-of-00002.safetensors",
935
+ "vae.decoder.up_blocks.3.0.conv.weight": "model-00002-of-00002.safetensors",
936
+ "vae.decoder.up_blocks.3.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
937
+ "vae.decoder.up_blocks.3.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
938
+ "vae.decoder.up_blocks.3.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
939
+ "vae.decoder.up_blocks.3.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
940
+ "vae.decoder.up_blocks.3.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
941
+ "vae.decoder.up_blocks.3.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
942
+ "vae.decoder.up_blocks.3.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
943
+ "vae.decoder.up_blocks.3.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
944
+ "vae.decoder.up_blocks.3.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
945
+ "vae.decoder.up_blocks.3.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
946
+ "vae.decoder.up_blocks.3.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
947
+ "vae.decoder.up_blocks.3.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
948
+ "vae.decoder.up_blocks.3.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
949
+ "vae.decoder.up_blocks.3.2.attn.norm_out.bias": "model-00002-of-00002.safetensors",
950
+ "vae.decoder.up_blocks.3.2.attn.norm_out.weight": "model-00002-of-00002.safetensors",
951
+ "vae.decoder.up_blocks.3.2.attn.to_k.weight": "model-00002-of-00002.safetensors",
952
+ "vae.decoder.up_blocks.3.2.attn.to_out.weight": "model-00002-of-00002.safetensors",
953
+ "vae.decoder.up_blocks.3.2.attn.to_q.weight": "model-00002-of-00002.safetensors",
954
+ "vae.decoder.up_blocks.3.2.attn.to_v.weight": "model-00002-of-00002.safetensors",
955
+ "vae.decoder.up_blocks.3.2.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
956
+ "vae.decoder.up_blocks.3.2.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
957
+ "vae.decoder.up_blocks.3.2.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
958
+ "vae.decoder.up_blocks.3.2.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
959
+ "vae.decoder.up_blocks.3.2.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
960
+ "vae.decoder.up_blocks.3.2.conv_out.norm.bias": "model-00002-of-00002.safetensors",
961
+ "vae.decoder.up_blocks.3.2.conv_out.norm.weight": "model-00002-of-00002.safetensors",
962
+ "vae.decoder.up_blocks.4.0.conv.bias": "model-00002-of-00002.safetensors",
963
+ "vae.decoder.up_blocks.4.0.conv.weight": "model-00002-of-00002.safetensors",
964
+ "vae.decoder.up_blocks.4.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
965
+ "vae.decoder.up_blocks.4.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
966
+ "vae.decoder.up_blocks.4.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
967
+ "vae.decoder.up_blocks.4.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
968
+ "vae.decoder.up_blocks.4.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
969
+ "vae.decoder.up_blocks.4.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
970
+ "vae.decoder.up_blocks.4.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
971
+ "vae.decoder.up_blocks.4.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
972
+ "vae.decoder.up_blocks.4.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
973
+ "vae.decoder.up_blocks.4.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
974
+ "vae.decoder.up_blocks.4.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
975
+ "vae.decoder.up_blocks.4.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
976
+ "vae.decoder.up_blocks.4.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
977
+ "vae.decoder.up_blocks.4.2.attn.norm_out.bias": "model-00002-of-00002.safetensors",
978
+ "vae.decoder.up_blocks.4.2.attn.norm_out.weight": "model-00002-of-00002.safetensors",
979
+ "vae.decoder.up_blocks.4.2.attn.to_k.weight": "model-00002-of-00002.safetensors",
980
+ "vae.decoder.up_blocks.4.2.attn.to_out.weight": "model-00002-of-00002.safetensors",
981
+ "vae.decoder.up_blocks.4.2.attn.to_q.weight": "model-00002-of-00002.safetensors",
982
+ "vae.decoder.up_blocks.4.2.attn.to_v.weight": "model-00002-of-00002.safetensors",
983
+ "vae.decoder.up_blocks.4.2.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
984
+ "vae.decoder.up_blocks.4.2.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
985
+ "vae.decoder.up_blocks.4.2.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
986
+ "vae.decoder.up_blocks.4.2.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
987
+ "vae.decoder.up_blocks.4.2.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
988
+ "vae.decoder.up_blocks.4.2.conv_out.norm.bias": "model-00002-of-00002.safetensors",
989
+ "vae.decoder.up_blocks.4.2.conv_out.norm.weight": "model-00002-of-00002.safetensors",
990
+ "vae.decoder.up_blocks.5.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
991
+ "vae.decoder.up_blocks.5.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
992
+ "vae.decoder.up_blocks.5.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
993
+ "vae.decoder.up_blocks.5.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
994
+ "vae.decoder.up_blocks.5.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
995
+ "vae.decoder.up_blocks.5.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
996
+ "vae.decoder.up_blocks.5.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
997
+ "vae.decoder.up_blocks.5.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
998
+ "vae.decoder.up_blocks.5.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
999
+ "vae.decoder.up_blocks.5.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1000
+ "vae.decoder.up_blocks.5.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1001
+ "vae.decoder.up_blocks.5.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1002
+ "vae.decoder.up_blocks.5.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1003
+ "vae.decoder.up_blocks.5.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1004
+ "vae.decoder.up_blocks.5.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1005
+ "vae.decoder.up_blocks.5.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
1006
+ "vae.decoder.up_blocks.5.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
1007
+ "vae.decoder.up_blocks.5.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
1008
+ "vae.decoder.up_blocks.5.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
1009
+ "vae.decoder.up_blocks.5.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1010
+ "vae.decoder.up_blocks.5.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1011
+ "vae.decoder.up_blocks.5.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1012
+ "vae.decoder.up_blocks.5.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1013
+ "vae.decoder.up_blocks.5.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1014
+ "vae.decoder.up_blocks.5.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1015
+ "vae.decoder.up_blocks.5.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1016
+ "vae.encoder.conv_in.conv.bias": "model-00002-of-00002.safetensors",
1017
+ "vae.encoder.conv_in.conv.weight": "model-00002-of-00002.safetensors",
1018
+ "vae.encoder.conv_out.bias": "model-00002-of-00002.safetensors",
1019
+ "vae.encoder.conv_out.weight": "model-00002-of-00002.safetensors",
1020
+ "vae.encoder.down_blocks.1.0.conv1.bias": "model-00002-of-00002.safetensors",
1021
+ "vae.encoder.down_blocks.1.0.conv1.weight": "model-00002-of-00002.safetensors",
1022
+ "vae.encoder.down_blocks.1.0.conv2.weight": "model-00002-of-00002.safetensors",
1023
+ "vae.encoder.down_blocks.1.0.norm.bias": "model-00002-of-00002.safetensors",
1024
+ "vae.encoder.down_blocks.1.0.norm.weight": "model-00002-of-00002.safetensors",
1025
+ "vae.encoder.down_blocks.1.1.conv1.bias": "model-00002-of-00002.safetensors",
1026
+ "vae.encoder.down_blocks.1.1.conv1.weight": "model-00002-of-00002.safetensors",
1027
+ "vae.encoder.down_blocks.1.1.conv2.weight": "model-00002-of-00002.safetensors",
1028
+ "vae.encoder.down_blocks.1.1.norm.bias": "model-00002-of-00002.safetensors",
1029
+ "vae.encoder.down_blocks.1.1.norm.weight": "model-00002-of-00002.safetensors",
1030
+ "vae.encoder.down_blocks.1.2.conv1.bias": "model-00002-of-00002.safetensors",
1031
+ "vae.encoder.down_blocks.1.2.conv1.weight": "model-00002-of-00002.safetensors",
1032
+ "vae.encoder.down_blocks.1.2.conv2.weight": "model-00002-of-00002.safetensors",
1033
+ "vae.encoder.down_blocks.1.2.norm.bias": "model-00002-of-00002.safetensors",
1034
+ "vae.encoder.down_blocks.1.2.norm.weight": "model-00002-of-00002.safetensors",
1035
+ "vae.encoder.down_blocks.1.3.conv1.bias": "model-00002-of-00002.safetensors",
1036
+ "vae.encoder.down_blocks.1.3.conv1.weight": "model-00002-of-00002.safetensors",
1037
+ "vae.encoder.down_blocks.1.3.conv2.weight": "model-00002-of-00002.safetensors",
1038
+ "vae.encoder.down_blocks.1.3.norm.bias": "model-00002-of-00002.safetensors",
1039
+ "vae.encoder.down_blocks.1.3.norm.weight": "model-00002-of-00002.safetensors",
1040
+ "vae.encoder.down_blocks.1.4.conv.bias": "model-00002-of-00002.safetensors",
1041
+ "vae.encoder.down_blocks.1.4.conv.weight": "model-00002-of-00002.safetensors",
1042
+ "vae.encoder.down_blocks.2.0.conv1.bias": "model-00002-of-00002.safetensors",
1043
+ "vae.encoder.down_blocks.2.0.conv1.weight": "model-00002-of-00002.safetensors",
1044
+ "vae.encoder.down_blocks.2.0.conv2.weight": "model-00002-of-00002.safetensors",
1045
+ "vae.encoder.down_blocks.2.0.norm.bias": "model-00002-of-00002.safetensors",
1046
+ "vae.encoder.down_blocks.2.0.norm.weight": "model-00002-of-00002.safetensors",
1047
+ "vae.encoder.down_blocks.2.1.conv1.bias": "model-00002-of-00002.safetensors",
1048
+ "vae.encoder.down_blocks.2.1.conv1.weight": "model-00002-of-00002.safetensors",
1049
+ "vae.encoder.down_blocks.2.1.conv2.weight": "model-00002-of-00002.safetensors",
1050
+ "vae.encoder.down_blocks.2.1.norm.bias": "model-00002-of-00002.safetensors",
1051
+ "vae.encoder.down_blocks.2.1.norm.weight": "model-00002-of-00002.safetensors",
1052
+ "vae.encoder.down_blocks.2.2.conv1.bias": "model-00002-of-00002.safetensors",
1053
+ "vae.encoder.down_blocks.2.2.conv1.weight": "model-00002-of-00002.safetensors",
1054
+ "vae.encoder.down_blocks.2.2.conv2.weight": "model-00002-of-00002.safetensors",
1055
+ "vae.encoder.down_blocks.2.2.norm.bias": "model-00002-of-00002.safetensors",
1056
+ "vae.encoder.down_blocks.2.2.norm.weight": "model-00002-of-00002.safetensors",
1057
+ "vae.encoder.down_blocks.2.3.conv1.bias": "model-00002-of-00002.safetensors",
1058
+ "vae.encoder.down_blocks.2.3.conv1.weight": "model-00002-of-00002.safetensors",
1059
+ "vae.encoder.down_blocks.2.3.conv2.weight": "model-00002-of-00002.safetensors",
1060
+ "vae.encoder.down_blocks.2.3.norm.bias": "model-00002-of-00002.safetensors",
1061
+ "vae.encoder.down_blocks.2.3.norm.weight": "model-00002-of-00002.safetensors",
1062
+ "vae.encoder.down_blocks.2.4.conv1.bias": "model-00002-of-00002.safetensors",
1063
+ "vae.encoder.down_blocks.2.4.conv1.weight": "model-00002-of-00002.safetensors",
1064
+ "vae.encoder.down_blocks.2.4.conv2.weight": "model-00002-of-00002.safetensors",
1065
+ "vae.encoder.down_blocks.2.4.norm.bias": "model-00002-of-00002.safetensors",
1066
+ "vae.encoder.down_blocks.2.4.norm.weight": "model-00002-of-00002.safetensors",
1067
+ "vae.encoder.down_blocks.2.5.conv1.bias": "model-00002-of-00002.safetensors",
1068
+ "vae.encoder.down_blocks.2.5.conv1.weight": "model-00002-of-00002.safetensors",
1069
+ "vae.encoder.down_blocks.2.5.conv2.weight": "model-00002-of-00002.safetensors",
1070
+ "vae.encoder.down_blocks.2.5.norm.bias": "model-00002-of-00002.safetensors",
1071
+ "vae.encoder.down_blocks.2.5.norm.weight": "model-00002-of-00002.safetensors",
1072
+ "vae.encoder.down_blocks.2.6.conv1.bias": "model-00002-of-00002.safetensors",
1073
+ "vae.encoder.down_blocks.2.6.conv1.weight": "model-00002-of-00002.safetensors",
1074
+ "vae.encoder.down_blocks.2.6.conv2.weight": "model-00002-of-00002.safetensors",
1075
+ "vae.encoder.down_blocks.2.6.norm.bias": "model-00002-of-00002.safetensors",
1076
+ "vae.encoder.down_blocks.2.6.norm.weight": "model-00002-of-00002.safetensors",
1077
+ "vae.encoder.down_blocks.2.7.conv1.bias": "model-00002-of-00002.safetensors",
1078
+ "vae.encoder.down_blocks.2.7.conv1.weight": "model-00002-of-00002.safetensors",
1079
+ "vae.encoder.down_blocks.2.7.conv2.weight": "model-00002-of-00002.safetensors",
1080
+ "vae.encoder.down_blocks.2.7.norm.bias": "model-00002-of-00002.safetensors",
1081
+ "vae.encoder.down_blocks.2.7.norm.weight": "model-00002-of-00002.safetensors",
1082
+ "vae.encoder.down_blocks.2.8.conv.bias": "model-00002-of-00002.safetensors",
1083
+ "vae.encoder.down_blocks.2.8.conv.weight": "model-00002-of-00002.safetensors",
1084
+ "vae.encoder.down_blocks.3.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1085
+ "vae.encoder.down_blocks.3.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1086
+ "vae.encoder.down_blocks.3.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
1087
+ "vae.encoder.down_blocks.3.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
1088
+ "vae.encoder.down_blocks.3.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
1089
+ "vae.encoder.down_blocks.3.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
1090
+ "vae.encoder.down_blocks.3.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1091
+ "vae.encoder.down_blocks.3.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1092
+ "vae.encoder.down_blocks.3.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1093
+ "vae.encoder.down_blocks.3.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1094
+ "vae.encoder.down_blocks.3.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1095
+ "vae.encoder.down_blocks.3.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1096
+ "vae.encoder.down_blocks.3.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1097
+ "vae.encoder.down_blocks.3.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1098
+ "vae.encoder.down_blocks.3.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1099
+ "vae.encoder.down_blocks.3.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
1100
+ "vae.encoder.down_blocks.3.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
1101
+ "vae.encoder.down_blocks.3.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
1102
+ "vae.encoder.down_blocks.3.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
1103
+ "vae.encoder.down_blocks.3.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1104
+ "vae.encoder.down_blocks.3.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1105
+ "vae.encoder.down_blocks.3.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1106
+ "vae.encoder.down_blocks.3.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1107
+ "vae.encoder.down_blocks.3.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1108
+ "vae.encoder.down_blocks.3.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1109
+ "vae.encoder.down_blocks.3.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1110
+ "vae.encoder.down_blocks.3.2.conv.bias": "model-00002-of-00002.safetensors",
1111
+ "vae.encoder.down_blocks.3.2.conv.weight": "model-00002-of-00002.safetensors",
1112
+ "vae.encoder.down_blocks.4.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1113
+ "vae.encoder.down_blocks.4.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1114
+ "vae.encoder.down_blocks.4.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
1115
+ "vae.encoder.down_blocks.4.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
1116
+ "vae.encoder.down_blocks.4.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
1117
+ "vae.encoder.down_blocks.4.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
1118
+ "vae.encoder.down_blocks.4.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1119
+ "vae.encoder.down_blocks.4.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1120
+ "vae.encoder.down_blocks.4.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1121
+ "vae.encoder.down_blocks.4.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1122
+ "vae.encoder.down_blocks.4.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1123
+ "vae.encoder.down_blocks.4.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1124
+ "vae.encoder.down_blocks.4.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1125
+ "vae.encoder.down_blocks.4.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1126
+ "vae.encoder.down_blocks.4.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1127
+ "vae.encoder.down_blocks.4.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
1128
+ "vae.encoder.down_blocks.4.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
1129
+ "vae.encoder.down_blocks.4.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
1130
+ "vae.encoder.down_blocks.4.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
1131
+ "vae.encoder.down_blocks.4.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1132
+ "vae.encoder.down_blocks.4.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1133
+ "vae.encoder.down_blocks.4.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1134
+ "vae.encoder.down_blocks.4.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1135
+ "vae.encoder.down_blocks.4.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1136
+ "vae.encoder.down_blocks.4.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1137
+ "vae.encoder.down_blocks.4.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1138
+ "vae.encoder.down_blocks.4.2.conv.bias": "model-00002-of-00002.safetensors",
1139
+ "vae.encoder.down_blocks.4.2.conv.weight": "model-00002-of-00002.safetensors",
1140
+ "vae.encoder.down_blocks.5.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1141
+ "vae.encoder.down_blocks.5.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1142
+ "vae.encoder.down_blocks.5.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
1143
+ "vae.encoder.down_blocks.5.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
1144
+ "vae.encoder.down_blocks.5.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
1145
+ "vae.encoder.down_blocks.5.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
1146
+ "vae.encoder.down_blocks.5.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1147
+ "vae.encoder.down_blocks.5.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1148
+ "vae.encoder.down_blocks.5.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1149
+ "vae.encoder.down_blocks.5.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1150
+ "vae.encoder.down_blocks.5.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1151
+ "vae.encoder.down_blocks.5.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1152
+ "vae.encoder.down_blocks.5.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1153
+ "vae.encoder.down_blocks.5.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1154
+ "vae.encoder.down_blocks.5.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1155
+ "vae.encoder.down_blocks.5.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
1156
+ "vae.encoder.down_blocks.5.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
1157
+ "vae.encoder.down_blocks.5.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
1158
+ "vae.encoder.down_blocks.5.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
1159
+ "vae.encoder.down_blocks.5.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1160
+ "vae.encoder.down_blocks.5.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1161
+ "vae.encoder.down_blocks.5.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1162
+ "vae.encoder.down_blocks.5.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1163
+ "vae.encoder.down_blocks.5.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1164
+ "vae.encoder.down_blocks.5.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1165
+ "vae.encoder.down_blocks.5.1.conv_out.norm.weight": "model-00002-of-00002.safetensors"
1166
+ }
1167
+ }
checkpoint-269000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017f3f205d5b27b57b6f358103d6ae7ceaeee5715f9dca3c968823851416cab4
3
+ size 11384525794
checkpoint-269000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b348881147ce29f9abe34722e8130b8b6c531609a919114ebb612fffb8523a60
3
+ size 16389
checkpoint-269000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8d794f493abd6d50d4a8c3c036216fc3806af12dc6cd552c5d5e723331a024
3
+ size 16389
checkpoint-269000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd3157f381041f5849f8d28eaaa05779c8c13d7896a7ed84afdb2f4a9078b2f
3
+ size 16389
checkpoint-269000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b55c0006a0ff308237d8f429714fabc79bb17e8e25d02fe4e8eacdc07d85c9
3
+ size 16389
checkpoint-269000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c85de41ff96611f1ed37ecd6aebf9e7391d4042b4124c302ce832581d33211cb
3
+ size 16389
checkpoint-269000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494c55ebc611806402fe547182d0be149b2a90cc9ea1ab1de7b118a9e3a9b510
3
+ size 16389
checkpoint-269000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49765b302d5fe4c9ae6c169864c185bfe6a7771a50ec2638da52b65f96571a20
3
+ size 16389
checkpoint-269000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe417fadbcfd4a7b4687953dbd06f28c8a753e67af47a29f3849fa2e4db71fca
3
+ size 16389
checkpoint-269000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9f59457f57861cd68d815032dd6389b011e92ecc3aa89c825a4d8d0aaa32a1
3
+ size 1465
checkpoint-269000/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89de10ca4408261816683b3627afc0597a662021e419649016e528a056eae184
3
+ size 41208418
checkpoint-269000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:901f4e3ae13ff83ae98e446ce35e228ac210a5ae0be9bddb408cbb5662d5dbb5
3
+ size 6417
checkpoint-270000/config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "ar_steps": 1,
3
+ "architectures": [
4
+ "DiffVLMBaseline"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "condition_layer": -1,
9
+ "eos_token_id": 151645,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1536,
12
+ "image_token_id": 151655,
13
+ "img_cross_attention_dim": 2048,
14
+ "img_diffuser_depth": 1,
15
+ "img_ffn_dim_multiplier": null,
16
+ "img_hidden_size": 1536,
17
+ "img_multiple_of": 256,
18
+ "img_norm_eps": 1e-05,
19
+ "img_num_attention_heads": 12,
20
+ "img_num_kv_heads": 12,
21
+ "img_qk_norm": true,
22
+ "in_channels": 32,
23
+ "initializer_range": 0.02,
24
+ "inject_img_diffuser": false,
25
+ "input_size": 32,
26
+ "intermediate_size": 8960,
27
+ "layer_group_size": 7,
28
+ "layerwise_start_idx": 0,
29
+ "lora_alpha": 16,
30
+ "lora_bias": "none",
31
+ "lora_dropout": 0.05,
32
+ "lora_enable": false,
33
+ "lora_r": 64,
34
+ "max_position_embeddings": 32768,
35
+ "max_window_layers": 28,
36
+ "model_type": "qwen2_vl",
37
+ "non_linearity": 1,
38
+ "norm_elementwise_affine": true,
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 28,
41
+ "num_key_value_heads": 2,
42
+ "patch_size": 1,
43
+ "repa_coeff": 0.5,
44
+ "repa_layers": null,
45
+ "repa_shared": false,
46
+ "rms_norm_eps": 1e-06,
47
+ "rope_scaling": {
48
+ "mrope_section": [
49
+ 16,
50
+ 24,
51
+ 24
52
+ ],
53
+ "rope_type": "default",
54
+ "type": "default"
55
+ },
56
+ "rope_theta": 1000000.0,
57
+ "sample_size": 128,
58
+ "sampling_steps": 28,
59
+ "sliding_window": null,
60
+ "tie_word_embeddings": true,
61
+ "torch_dtype": "bfloat16",
62
+ "transformers_version": "4.47.0",
63
+ "use_cache": true,
64
+ "use_repa": false,
65
+ "use_residual_attn": false,
66
+ "use_sliding_window": false,
67
+ "vae_path": "mit-han-lab/dc-ae-f32c32-in-1.0-diffusers",
68
+ "video_token_id": 151656,
69
+ "vision_config": {
70
+ "hidden_size": 1536,
71
+ "in_chans": 3,
72
+ "model_type": "qwen2_vl",
73
+ "spatial_patch_size": 14
74
+ },
75
+ "vision_end_token_id": 151653,
76
+ "vision_start_token_id": 151652,
77
+ "vision_token_id": 151654,
78
+ "vocab_size": 151936
79
+ }
checkpoint-270000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.47.0"
6
+ }
checkpoint-270000/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7256c94f282d838ee7f7a49ba5a10a310424af6e7b9dbb2f4c28a811797eb7a9
3
+ size 4980624888
checkpoint-270000/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bcabcd5a1c2704419c156af4f540664bbdbf39af9ede02542759f694550e37f
3
+ size 1918602176
checkpoint-270000/model.safetensors.index.json ADDED
@@ -0,0 +1,1167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6899096400
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "img2text.bias": "model-00001-of-00002.safetensors",
8
+ "img2text.weight": "model-00001-of-00002.safetensors",
9
+ "img_norm_out.linear_1.bias": "model-00001-of-00002.safetensors",
10
+ "img_norm_out.linear_1.weight": "model-00001-of-00002.safetensors",
11
+ "img_norm_out.linear_2.bias": "model-00001-of-00002.safetensors",
12
+ "img_norm_out.linear_2.weight": "model-00001-of-00002.safetensors",
13
+ "layers.0.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
14
+ "layers.0.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
15
+ "layers.0.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
16
+ "layers.0.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
17
+ "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
23
+ "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
24
+ "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
26
+ "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
27
+ "layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
28
+ "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
29
+ "layers.1.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
30
+ "layers.1.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
31
+ "layers.1.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
32
+ "layers.1.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
33
+ "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
35
+ "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
36
+ "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
37
+ "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
39
+ "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
42
+ "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
44
+ "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
45
+ "layers.10.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
46
+ "layers.10.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
47
+ "layers.10.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
48
+ "layers.10.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
49
+ "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
51
+ "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
52
+ "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
53
+ "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
55
+ "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
56
+ "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
57
+ "layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
58
+ "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
59
+ "layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
60
+ "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "layers.11.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
62
+ "layers.11.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
63
+ "layers.11.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
64
+ "layers.11.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
65
+ "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
67
+ "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
68
+ "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
69
+ "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
71
+ "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
72
+ "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
73
+ "layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
74
+ "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
75
+ "layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
76
+ "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
77
+ "layers.12.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
78
+ "layers.12.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
79
+ "layers.12.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
80
+ "layers.12.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
81
+ "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
83
+ "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
84
+ "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
87
+ "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
88
+ "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
89
+ "layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
90
+ "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
91
+ "layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
92
+ "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
93
+ "layers.13.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
94
+ "layers.13.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
95
+ "layers.13.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
96
+ "layers.13.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
97
+ "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
103
+ "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
106
+ "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
108
+ "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
109
+ "layers.14.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
110
+ "layers.14.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
111
+ "layers.14.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
112
+ "layers.14.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
113
+ "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
114
+ "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
115
+ "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
116
+ "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
117
+ "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
119
+ "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
120
+ "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
121
+ "layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
122
+ "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
124
+ "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "layers.15.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
126
+ "layers.15.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
127
+ "layers.15.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
128
+ "layers.15.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
129
+ "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
135
+ "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
138
+ "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
140
+ "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "layers.16.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
142
+ "layers.16.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
143
+ "layers.16.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
144
+ "layers.16.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
145
+ "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
147
+ "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
148
+ "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
149
+ "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
+ "layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
151
+ "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
152
+ "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
153
+ "layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
154
+ "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
155
+ "layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
156
+ "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
157
+ "layers.17.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
158
+ "layers.17.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
159
+ "layers.17.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
160
+ "layers.17.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
161
+ "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
163
+ "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
164
+ "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
165
+ "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
167
+ "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
168
+ "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
170
+ "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
171
+ "layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
172
+ "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
173
+ "layers.18.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
174
+ "layers.18.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
175
+ "layers.18.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
176
+ "layers.18.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
177
+ "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
178
+ "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
179
+ "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
180
+ "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
181
+ "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
183
+ "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
184
+ "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
185
+ "layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
186
+ "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
188
+ "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
189
+ "layers.19.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
190
+ "layers.19.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
191
+ "layers.19.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
192
+ "layers.19.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
193
+ "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
195
+ "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
196
+ "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
197
+ "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
199
+ "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
200
+ "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
201
+ "layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
202
+ "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
203
+ "layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
204
+ "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "layers.2.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
206
+ "layers.2.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
207
+ "layers.2.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
208
+ "layers.2.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
209
+ "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
210
+ "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
211
+ "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
212
+ "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
213
+ "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
214
+ "layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
215
+ "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
216
+ "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
217
+ "layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
218
+ "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
219
+ "layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
220
+ "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
+ "layers.20.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
222
+ "layers.20.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
223
+ "layers.20.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
224
+ "layers.20.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
225
+ "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
226
+ "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
227
+ "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
228
+ "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
229
+ "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
230
+ "layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
231
+ "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
232
+ "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
233
+ "layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
234
+ "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
235
+ "layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
236
+ "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
237
+ "layers.21.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
238
+ "layers.21.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
239
+ "layers.21.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
240
+ "layers.21.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
241
+ "layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
243
+ "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
244
+ "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
+ "layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
247
+ "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
250
+ "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
251
+ "layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
252
+ "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
253
+ "layers.22.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
254
+ "layers.22.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
255
+ "layers.22.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
256
+ "layers.22.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
257
+ "layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
258
+ "layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
259
+ "layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
260
+ "layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
261
+ "layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
263
+ "layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
264
+ "layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
265
+ "layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
266
+ "layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
267
+ "layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
268
+ "layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
+ "layers.23.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
270
+ "layers.23.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
271
+ "layers.23.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
272
+ "layers.23.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
273
+ "layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
275
+ "layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
276
+ "layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
277
+ "layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
279
+ "layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
281
+ "layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
282
+ "layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
284
+ "layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
285
+ "layers.24.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
286
+ "layers.24.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
287
+ "layers.24.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
288
+ "layers.24.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
289
+ "layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
290
+ "layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
291
+ "layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
292
+ "layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
293
+ "layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
294
+ "layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
295
+ "layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
296
+ "layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
297
+ "layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
298
+ "layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
299
+ "layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
300
+ "layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
301
+ "layers.25.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
302
+ "layers.25.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
303
+ "layers.25.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
304
+ "layers.25.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
305
+ "layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
306
+ "layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
307
+ "layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
308
+ "layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
309
+ "layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
310
+ "layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
311
+ "layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
312
+ "layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
313
+ "layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
314
+ "layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
315
+ "layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
316
+ "layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
317
+ "layers.26.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
318
+ "layers.26.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
319
+ "layers.26.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
320
+ "layers.26.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
321
+ "layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
322
+ "layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
323
+ "layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
324
+ "layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
325
+ "layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
326
+ "layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
327
+ "layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
328
+ "layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
329
+ "layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
330
+ "layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
+ "layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
332
+ "layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "layers.27.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
334
+ "layers.27.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
335
+ "layers.27.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
336
+ "layers.27.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
337
+ "layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
338
+ "layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
339
+ "layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
340
+ "layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
341
+ "layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
342
+ "layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
343
+ "layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
344
+ "layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
345
+ "layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
346
+ "layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
347
+ "layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
348
+ "layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
+ "layers.3.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
350
+ "layers.3.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
351
+ "layers.3.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
352
+ "layers.3.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
353
+ "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
354
+ "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
355
+ "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
356
+ "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
357
+ "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
358
+ "layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
359
+ "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
360
+ "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
361
+ "layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
362
+ "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
363
+ "layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
364
+ "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
365
+ "layers.4.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
366
+ "layers.4.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
367
+ "layers.4.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
368
+ "layers.4.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
369
+ "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
370
+ "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
371
+ "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
372
+ "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
373
+ "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
374
+ "layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
375
+ "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
376
+ "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
377
+ "layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
378
+ "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
379
+ "layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
380
+ "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
381
+ "layers.5.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
382
+ "layers.5.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
383
+ "layers.5.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
384
+ "layers.5.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
385
+ "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
386
+ "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
387
+ "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
388
+ "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
389
+ "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
390
+ "layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
391
+ "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
392
+ "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
393
+ "layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
394
+ "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
395
+ "layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
396
+ "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
397
+ "layers.6.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
398
+ "layers.6.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
399
+ "layers.6.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
400
+ "layers.6.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
401
+ "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
402
+ "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
403
+ "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
404
+ "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
405
+ "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
406
+ "layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
407
+ "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
408
+ "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
409
+ "layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
410
+ "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
411
+ "layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
412
+ "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
413
+ "layers.7.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
414
+ "layers.7.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
415
+ "layers.7.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
416
+ "layers.7.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
417
+ "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
418
+ "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
419
+ "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
420
+ "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
421
+ "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
422
+ "layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
423
+ "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
424
+ "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
425
+ "layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
426
+ "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
427
+ "layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
428
+ "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
429
+ "layers.8.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
430
+ "layers.8.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
431
+ "layers.8.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
432
+ "layers.8.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
433
+ "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
434
+ "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
435
+ "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
436
+ "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
437
+ "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
438
+ "layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
439
+ "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
440
+ "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
441
+ "layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
442
+ "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
443
+ "layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
444
+ "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
445
+ "layers.9.img_post_ffn_norm.weight": "model-00001-of-00002.safetensors",
446
+ "layers.9.img_post_mixed_attn_norm.weight": "model-00001-of-00002.safetensors",
447
+ "layers.9.img_scale_shift.linear.bias": "model-00001-of-00002.safetensors",
448
+ "layers.9.img_scale_shift.linear.weight": "model-00001-of-00002.safetensors",
449
+ "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
450
+ "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
451
+ "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
452
+ "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
453
+ "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
454
+ "layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
455
+ "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
456
+ "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
457
+ "layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
458
+ "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
459
+ "layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
460
+ "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
461
+ "norm.weight": "model-00002-of-00002.safetensors",
462
+ "patch_embedder.proj.bias": "model-00001-of-00002.safetensors",
463
+ "patch_embedder.proj.weight": "model-00001-of-00002.safetensors",
464
+ "t_embedder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors",
465
+ "t_embedder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors",
466
+ "t_embedder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors",
467
+ "t_embedder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors",
468
+ "txt_layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
469
+ "txt_layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
470
+ "txt_layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
471
+ "txt_layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
472
+ "txt_layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
473
+ "txt_layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
474
+ "txt_layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
475
+ "txt_layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
476
+ "txt_layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
477
+ "txt_layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
478
+ "txt_layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
479
+ "txt_layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
480
+ "txt_layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
481
+ "txt_layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
482
+ "txt_layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
483
+ "txt_layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
484
+ "txt_layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
485
+ "txt_layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
486
+ "txt_layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
487
+ "txt_layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
488
+ "txt_layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
489
+ "txt_layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
490
+ "txt_layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
491
+ "txt_layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
492
+ "txt_layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
493
+ "txt_layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
494
+ "txt_layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
495
+ "txt_layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
496
+ "txt_layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
497
+ "txt_layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
498
+ "txt_layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
499
+ "txt_layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
500
+ "txt_layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
501
+ "txt_layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
502
+ "txt_layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
503
+ "txt_layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
504
+ "txt_layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
505
+ "txt_layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
506
+ "txt_layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
507
+ "txt_layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
508
+ "txt_layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
509
+ "txt_layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
510
+ "txt_layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
511
+ "txt_layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
512
+ "txt_layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
513
+ "txt_layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
514
+ "txt_layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
515
+ "txt_layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
516
+ "txt_layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
517
+ "txt_layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
518
+ "txt_layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
519
+ "txt_layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
520
+ "txt_layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
521
+ "txt_layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
522
+ "txt_layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
523
+ "txt_layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
524
+ "txt_layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
525
+ "txt_layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
526
+ "txt_layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
527
+ "txt_layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
528
+ "txt_layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
529
+ "txt_layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
530
+ "txt_layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
531
+ "txt_layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
532
+ "txt_layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
533
+ "txt_layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
534
+ "txt_layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
535
+ "txt_layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
536
+ "txt_layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
537
+ "txt_layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
538
+ "txt_layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
539
+ "txt_layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
540
+ "txt_layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
541
+ "txt_layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
542
+ "txt_layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
543
+ "txt_layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
544
+ "txt_layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
545
+ "txt_layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
546
+ "txt_layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
547
+ "txt_layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
548
+ "txt_layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
549
+ "txt_layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
550
+ "txt_layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
551
+ "txt_layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
552
+ "txt_layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
553
+ "txt_layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
554
+ "txt_layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
555
+ "txt_layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
556
+ "txt_layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
557
+ "txt_layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
558
+ "txt_layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
559
+ "txt_layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
560
+ "txt_layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
561
+ "txt_layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
562
+ "txt_layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
563
+ "txt_layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
564
+ "txt_layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
565
+ "txt_layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
566
+ "txt_layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
567
+ "txt_layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
568
+ "txt_layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
569
+ "txt_layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
570
+ "txt_layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
571
+ "txt_layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
572
+ "txt_layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
573
+ "txt_layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
574
+ "txt_layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
575
+ "txt_layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
576
+ "txt_layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
577
+ "txt_layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
578
+ "txt_layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
579
+ "txt_layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
580
+ "txt_layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
581
+ "txt_layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
582
+ "txt_layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
583
+ "txt_layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
584
+ "txt_layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
585
+ "txt_layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
586
+ "txt_layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
587
+ "txt_layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
588
+ "txt_layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
589
+ "txt_layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
590
+ "txt_layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
591
+ "txt_layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
592
+ "txt_layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
593
+ "txt_layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
594
+ "txt_layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
595
+ "txt_layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
596
+ "txt_layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
597
+ "txt_layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
598
+ "txt_layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
599
+ "txt_layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
600
+ "txt_layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
601
+ "txt_layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
602
+ "txt_layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
603
+ "txt_layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
604
+ "txt_layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
605
+ "txt_layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
606
+ "txt_layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
607
+ "txt_layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
608
+ "txt_layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
609
+ "txt_layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
610
+ "txt_layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
611
+ "txt_layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
612
+ "txt_layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
613
+ "txt_layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
614
+ "txt_layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
615
+ "txt_layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
616
+ "txt_layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
617
+ "txt_layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
618
+ "txt_layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
619
+ "txt_layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
620
+ "txt_layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
621
+ "txt_layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
622
+ "txt_layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
623
+ "txt_layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
624
+ "txt_layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
625
+ "txt_layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
626
+ "txt_layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
627
+ "txt_layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
628
+ "txt_layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
629
+ "txt_layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
630
+ "txt_layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
631
+ "txt_layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
632
+ "txt_layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
633
+ "txt_layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
634
+ "txt_layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
635
+ "txt_layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
636
+ "txt_layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
637
+ "txt_layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
638
+ "txt_layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
639
+ "txt_layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
640
+ "txt_layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
641
+ "txt_layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
642
+ "txt_layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
643
+ "txt_layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
644
+ "txt_layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
645
+ "txt_layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
646
+ "txt_layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
647
+ "txt_layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
648
+ "txt_layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
649
+ "txt_layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
650
+ "txt_layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
651
+ "txt_layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
652
+ "txt_layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
653
+ "txt_layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
654
+ "txt_layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
655
+ "txt_layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
656
+ "txt_layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
657
+ "txt_layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
658
+ "txt_layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
659
+ "txt_layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
660
+ "txt_layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
661
+ "txt_layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
662
+ "txt_layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
663
+ "txt_layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
664
+ "txt_layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
665
+ "txt_layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
666
+ "txt_layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
667
+ "txt_layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
668
+ "txt_layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
669
+ "txt_layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
670
+ "txt_layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
671
+ "txt_layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
672
+ "txt_layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
673
+ "txt_layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
674
+ "txt_layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
675
+ "txt_layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
676
+ "txt_layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
677
+ "txt_layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
678
+ "txt_layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
679
+ "txt_layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
680
+ "txt_layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
681
+ "txt_layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
682
+ "txt_layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
683
+ "txt_layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
684
+ "txt_layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
685
+ "txt_layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
686
+ "txt_layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
687
+ "txt_layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
688
+ "txt_layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
689
+ "txt_layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
690
+ "txt_layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
691
+ "txt_layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
692
+ "txt_layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
693
+ "txt_layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
694
+ "txt_layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
695
+ "txt_layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
696
+ "txt_layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
697
+ "txt_layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
698
+ "txt_layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
699
+ "txt_layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
700
+ "txt_layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
701
+ "txt_layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
702
+ "txt_layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
703
+ "txt_layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
704
+ "txt_layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
705
+ "txt_layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
706
+ "txt_layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
707
+ "txt_layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
708
+ "txt_layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
709
+ "txt_layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
710
+ "txt_layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
711
+ "txt_layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
712
+ "txt_layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
713
+ "txt_layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
714
+ "txt_layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
715
+ "txt_layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
716
+ "txt_layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
717
+ "txt_layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
718
+ "txt_layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
719
+ "txt_layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
720
+ "txt_layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
721
+ "txt_layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
722
+ "txt_layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
723
+ "txt_layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
724
+ "txt_layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
725
+ "txt_layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
726
+ "txt_layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
727
+ "txt_layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
728
+ "txt_layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
729
+ "txt_layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
730
+ "txt_layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
731
+ "txt_layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
732
+ "txt_layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
733
+ "txt_layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
734
+ "txt_layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
735
+ "txt_layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
736
+ "txt_layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
737
+ "txt_layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
738
+ "txt_layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
739
+ "txt_layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
740
+ "txt_layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
741
+ "txt_layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
742
+ "txt_layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
743
+ "txt_layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
744
+ "txt_layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
745
+ "txt_layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
746
+ "txt_layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
747
+ "txt_layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
748
+ "txt_layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
749
+ "txt_layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
750
+ "txt_layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
751
+ "txt_layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
752
+ "txt_layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
753
+ "txt_layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
754
+ "txt_layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
755
+ "txt_layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
756
+ "txt_layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
757
+ "txt_layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
758
+ "txt_layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
759
+ "txt_layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
760
+ "txt_layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
761
+ "txt_layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
762
+ "txt_layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
763
+ "txt_layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
764
+ "txt_layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
765
+ "txt_layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
766
+ "txt_layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
767
+ "txt_layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
768
+ "txt_layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
769
+ "txt_layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
770
+ "txt_layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
771
+ "txt_layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
772
+ "txt_layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
773
+ "txt_layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
774
+ "txt_layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
775
+ "txt_layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
776
+ "txt_layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
777
+ "txt_layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
778
+ "txt_layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
779
+ "txt_layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
780
+ "txt_layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
781
+ "txt_layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
782
+ "txt_layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
783
+ "txt_layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
784
+ "txt_layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
785
+ "txt_layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
786
+ "txt_layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
787
+ "txt_layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
788
+ "txt_layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
789
+ "txt_layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
790
+ "txt_layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
791
+ "txt_layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
792
+ "txt_layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
793
+ "txt_layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
794
+ "txt_layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
795
+ "txt_layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
796
+ "txt_layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
797
+ "txt_layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
798
+ "txt_layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
799
+ "txt_layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
800
+ "txt_layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
801
+ "txt_layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
802
+ "txt_layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
803
+ "txt_layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
804
+ "vae.decoder.conv_in.bias": "model-00002-of-00002.safetensors",
805
+ "vae.decoder.conv_in.weight": "model-00002-of-00002.safetensors",
806
+ "vae.decoder.conv_out.conv.bias": "model-00002-of-00002.safetensors",
807
+ "vae.decoder.conv_out.conv.weight": "model-00002-of-00002.safetensors",
808
+ "vae.decoder.norm_out.bias": "model-00002-of-00002.safetensors",
809
+ "vae.decoder.norm_out.weight": "model-00002-of-00002.safetensors",
810
+ "vae.decoder.up_blocks.1.0.conv.bias": "model-00002-of-00002.safetensors",
811
+ "vae.decoder.up_blocks.1.0.conv.weight": "model-00002-of-00002.safetensors",
812
+ "vae.decoder.up_blocks.1.1.conv1.bias": "model-00002-of-00002.safetensors",
813
+ "vae.decoder.up_blocks.1.1.conv1.weight": "model-00002-of-00002.safetensors",
814
+ "vae.decoder.up_blocks.1.1.conv2.weight": "model-00002-of-00002.safetensors",
815
+ "vae.decoder.up_blocks.1.1.norm.bias": "model-00002-of-00002.safetensors",
816
+ "vae.decoder.up_blocks.1.1.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
817
+ "vae.decoder.up_blocks.1.1.norm.running_mean": "model-00002-of-00002.safetensors",
818
+ "vae.decoder.up_blocks.1.1.norm.running_var": "model-00002-of-00002.safetensors",
819
+ "vae.decoder.up_blocks.1.1.norm.weight": "model-00002-of-00002.safetensors",
820
+ "vae.decoder.up_blocks.1.2.conv1.bias": "model-00002-of-00002.safetensors",
821
+ "vae.decoder.up_blocks.1.2.conv1.weight": "model-00002-of-00002.safetensors",
822
+ "vae.decoder.up_blocks.1.2.conv2.weight": "model-00002-of-00002.safetensors",
823
+ "vae.decoder.up_blocks.1.2.norm.bias": "model-00002-of-00002.safetensors",
824
+ "vae.decoder.up_blocks.1.2.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
825
+ "vae.decoder.up_blocks.1.2.norm.running_mean": "model-00002-of-00002.safetensors",
826
+ "vae.decoder.up_blocks.1.2.norm.running_var": "model-00002-of-00002.safetensors",
827
+ "vae.decoder.up_blocks.1.2.norm.weight": "model-00002-of-00002.safetensors",
828
+ "vae.decoder.up_blocks.1.3.conv1.bias": "model-00002-of-00002.safetensors",
829
+ "vae.decoder.up_blocks.1.3.conv1.weight": "model-00002-of-00002.safetensors",
830
+ "vae.decoder.up_blocks.1.3.conv2.weight": "model-00002-of-00002.safetensors",
831
+ "vae.decoder.up_blocks.1.3.norm.bias": "model-00002-of-00002.safetensors",
832
+ "vae.decoder.up_blocks.1.3.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
833
+ "vae.decoder.up_blocks.1.3.norm.running_mean": "model-00002-of-00002.safetensors",
834
+ "vae.decoder.up_blocks.1.3.norm.running_var": "model-00002-of-00002.safetensors",
835
+ "vae.decoder.up_blocks.1.3.norm.weight": "model-00002-of-00002.safetensors",
836
+ "vae.decoder.up_blocks.1.4.conv1.bias": "model-00002-of-00002.safetensors",
837
+ "vae.decoder.up_blocks.1.4.conv1.weight": "model-00002-of-00002.safetensors",
838
+ "vae.decoder.up_blocks.1.4.conv2.weight": "model-00002-of-00002.safetensors",
839
+ "vae.decoder.up_blocks.1.4.norm.bias": "model-00002-of-00002.safetensors",
840
+ "vae.decoder.up_blocks.1.4.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
841
+ "vae.decoder.up_blocks.1.4.norm.running_mean": "model-00002-of-00002.safetensors",
842
+ "vae.decoder.up_blocks.1.4.norm.running_var": "model-00002-of-00002.safetensors",
843
+ "vae.decoder.up_blocks.1.4.norm.weight": "model-00002-of-00002.safetensors",
844
+ "vae.decoder.up_blocks.1.5.conv1.bias": "model-00002-of-00002.safetensors",
845
+ "vae.decoder.up_blocks.1.5.conv1.weight": "model-00002-of-00002.safetensors",
846
+ "vae.decoder.up_blocks.1.5.conv2.weight": "model-00002-of-00002.safetensors",
847
+ "vae.decoder.up_blocks.1.5.norm.bias": "model-00002-of-00002.safetensors",
848
+ "vae.decoder.up_blocks.1.5.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
849
+ "vae.decoder.up_blocks.1.5.norm.running_mean": "model-00002-of-00002.safetensors",
850
+ "vae.decoder.up_blocks.1.5.norm.running_var": "model-00002-of-00002.safetensors",
851
+ "vae.decoder.up_blocks.1.5.norm.weight": "model-00002-of-00002.safetensors",
852
+ "vae.decoder.up_blocks.2.0.conv.bias": "model-00002-of-00002.safetensors",
853
+ "vae.decoder.up_blocks.2.0.conv.weight": "model-00002-of-00002.safetensors",
854
+ "vae.decoder.up_blocks.2.1.conv1.bias": "model-00002-of-00002.safetensors",
855
+ "vae.decoder.up_blocks.2.1.conv1.weight": "model-00002-of-00002.safetensors",
856
+ "vae.decoder.up_blocks.2.1.conv2.weight": "model-00002-of-00002.safetensors",
857
+ "vae.decoder.up_blocks.2.1.norm.bias": "model-00002-of-00002.safetensors",
858
+ "vae.decoder.up_blocks.2.1.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
859
+ "vae.decoder.up_blocks.2.1.norm.running_mean": "model-00002-of-00002.safetensors",
860
+ "vae.decoder.up_blocks.2.1.norm.running_var": "model-00002-of-00002.safetensors",
861
+ "vae.decoder.up_blocks.2.1.norm.weight": "model-00002-of-00002.safetensors",
862
+ "vae.decoder.up_blocks.2.10.conv1.bias": "model-00002-of-00002.safetensors",
863
+ "vae.decoder.up_blocks.2.10.conv1.weight": "model-00002-of-00002.safetensors",
864
+ "vae.decoder.up_blocks.2.10.conv2.weight": "model-00002-of-00002.safetensors",
865
+ "vae.decoder.up_blocks.2.10.norm.bias": "model-00002-of-00002.safetensors",
866
+ "vae.decoder.up_blocks.2.10.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
867
+ "vae.decoder.up_blocks.2.10.norm.running_mean": "model-00002-of-00002.safetensors",
868
+ "vae.decoder.up_blocks.2.10.norm.running_var": "model-00002-of-00002.safetensors",
869
+ "vae.decoder.up_blocks.2.10.norm.weight": "model-00002-of-00002.safetensors",
870
+ "vae.decoder.up_blocks.2.2.conv1.bias": "model-00002-of-00002.safetensors",
871
+ "vae.decoder.up_blocks.2.2.conv1.weight": "model-00002-of-00002.safetensors",
872
+ "vae.decoder.up_blocks.2.2.conv2.weight": "model-00002-of-00002.safetensors",
873
+ "vae.decoder.up_blocks.2.2.norm.bias": "model-00002-of-00002.safetensors",
874
+ "vae.decoder.up_blocks.2.2.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
875
+ "vae.decoder.up_blocks.2.2.norm.running_mean": "model-00002-of-00002.safetensors",
876
+ "vae.decoder.up_blocks.2.2.norm.running_var": "model-00002-of-00002.safetensors",
877
+ "vae.decoder.up_blocks.2.2.norm.weight": "model-00002-of-00002.safetensors",
878
+ "vae.decoder.up_blocks.2.3.conv1.bias": "model-00002-of-00002.safetensors",
879
+ "vae.decoder.up_blocks.2.3.conv1.weight": "model-00002-of-00002.safetensors",
880
+ "vae.decoder.up_blocks.2.3.conv2.weight": "model-00002-of-00002.safetensors",
881
+ "vae.decoder.up_blocks.2.3.norm.bias": "model-00002-of-00002.safetensors",
882
+ "vae.decoder.up_blocks.2.3.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
883
+ "vae.decoder.up_blocks.2.3.norm.running_mean": "model-00002-of-00002.safetensors",
884
+ "vae.decoder.up_blocks.2.3.norm.running_var": "model-00002-of-00002.safetensors",
885
+ "vae.decoder.up_blocks.2.3.norm.weight": "model-00002-of-00002.safetensors",
886
+ "vae.decoder.up_blocks.2.4.conv1.bias": "model-00002-of-00002.safetensors",
887
+ "vae.decoder.up_blocks.2.4.conv1.weight": "model-00002-of-00002.safetensors",
888
+ "vae.decoder.up_blocks.2.4.conv2.weight": "model-00002-of-00002.safetensors",
889
+ "vae.decoder.up_blocks.2.4.norm.bias": "model-00002-of-00002.safetensors",
890
+ "vae.decoder.up_blocks.2.4.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
891
+ "vae.decoder.up_blocks.2.4.norm.running_mean": "model-00002-of-00002.safetensors",
892
+ "vae.decoder.up_blocks.2.4.norm.running_var": "model-00002-of-00002.safetensors",
893
+ "vae.decoder.up_blocks.2.4.norm.weight": "model-00002-of-00002.safetensors",
894
+ "vae.decoder.up_blocks.2.5.conv1.bias": "model-00002-of-00002.safetensors",
895
+ "vae.decoder.up_blocks.2.5.conv1.weight": "model-00002-of-00002.safetensors",
896
+ "vae.decoder.up_blocks.2.5.conv2.weight": "model-00002-of-00002.safetensors",
897
+ "vae.decoder.up_blocks.2.5.norm.bias": "model-00002-of-00002.safetensors",
898
+ "vae.decoder.up_blocks.2.5.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
899
+ "vae.decoder.up_blocks.2.5.norm.running_mean": "model-00002-of-00002.safetensors",
900
+ "vae.decoder.up_blocks.2.5.norm.running_var": "model-00002-of-00002.safetensors",
901
+ "vae.decoder.up_blocks.2.5.norm.weight": "model-00002-of-00002.safetensors",
902
+ "vae.decoder.up_blocks.2.6.conv1.bias": "model-00002-of-00002.safetensors",
903
+ "vae.decoder.up_blocks.2.6.conv1.weight": "model-00002-of-00002.safetensors",
904
+ "vae.decoder.up_blocks.2.6.conv2.weight": "model-00002-of-00002.safetensors",
905
+ "vae.decoder.up_blocks.2.6.norm.bias": "model-00002-of-00002.safetensors",
906
+ "vae.decoder.up_blocks.2.6.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
907
+ "vae.decoder.up_blocks.2.6.norm.running_mean": "model-00002-of-00002.safetensors",
908
+ "vae.decoder.up_blocks.2.6.norm.running_var": "model-00002-of-00002.safetensors",
909
+ "vae.decoder.up_blocks.2.6.norm.weight": "model-00002-of-00002.safetensors",
910
+ "vae.decoder.up_blocks.2.7.conv1.bias": "model-00002-of-00002.safetensors",
911
+ "vae.decoder.up_blocks.2.7.conv1.weight": "model-00002-of-00002.safetensors",
912
+ "vae.decoder.up_blocks.2.7.conv2.weight": "model-00002-of-00002.safetensors",
913
+ "vae.decoder.up_blocks.2.7.norm.bias": "model-00002-of-00002.safetensors",
914
+ "vae.decoder.up_blocks.2.7.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
915
+ "vae.decoder.up_blocks.2.7.norm.running_mean": "model-00002-of-00002.safetensors",
916
+ "vae.decoder.up_blocks.2.7.norm.running_var": "model-00002-of-00002.safetensors",
917
+ "vae.decoder.up_blocks.2.7.norm.weight": "model-00002-of-00002.safetensors",
918
+ "vae.decoder.up_blocks.2.8.conv1.bias": "model-00002-of-00002.safetensors",
919
+ "vae.decoder.up_blocks.2.8.conv1.weight": "model-00002-of-00002.safetensors",
920
+ "vae.decoder.up_blocks.2.8.conv2.weight": "model-00002-of-00002.safetensors",
921
+ "vae.decoder.up_blocks.2.8.norm.bias": "model-00002-of-00002.safetensors",
922
+ "vae.decoder.up_blocks.2.8.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
923
+ "vae.decoder.up_blocks.2.8.norm.running_mean": "model-00002-of-00002.safetensors",
924
+ "vae.decoder.up_blocks.2.8.norm.running_var": "model-00002-of-00002.safetensors",
925
+ "vae.decoder.up_blocks.2.8.norm.weight": "model-00002-of-00002.safetensors",
926
+ "vae.decoder.up_blocks.2.9.conv1.bias": "model-00002-of-00002.safetensors",
927
+ "vae.decoder.up_blocks.2.9.conv1.weight": "model-00002-of-00002.safetensors",
928
+ "vae.decoder.up_blocks.2.9.conv2.weight": "model-00002-of-00002.safetensors",
929
+ "vae.decoder.up_blocks.2.9.norm.bias": "model-00002-of-00002.safetensors",
930
+ "vae.decoder.up_blocks.2.9.norm.num_batches_tracked": "model-00002-of-00002.safetensors",
931
+ "vae.decoder.up_blocks.2.9.norm.running_mean": "model-00002-of-00002.safetensors",
932
+ "vae.decoder.up_blocks.2.9.norm.running_var": "model-00002-of-00002.safetensors",
933
+ "vae.decoder.up_blocks.2.9.norm.weight": "model-00002-of-00002.safetensors",
934
+ "vae.decoder.up_blocks.3.0.conv.bias": "model-00002-of-00002.safetensors",
935
+ "vae.decoder.up_blocks.3.0.conv.weight": "model-00002-of-00002.safetensors",
936
+ "vae.decoder.up_blocks.3.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
937
+ "vae.decoder.up_blocks.3.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
938
+ "vae.decoder.up_blocks.3.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
939
+ "vae.decoder.up_blocks.3.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
940
+ "vae.decoder.up_blocks.3.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
941
+ "vae.decoder.up_blocks.3.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
942
+ "vae.decoder.up_blocks.3.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
943
+ "vae.decoder.up_blocks.3.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
944
+ "vae.decoder.up_blocks.3.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
945
+ "vae.decoder.up_blocks.3.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
946
+ "vae.decoder.up_blocks.3.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
947
+ "vae.decoder.up_blocks.3.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
948
+ "vae.decoder.up_blocks.3.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
949
+ "vae.decoder.up_blocks.3.2.attn.norm_out.bias": "model-00002-of-00002.safetensors",
950
+ "vae.decoder.up_blocks.3.2.attn.norm_out.weight": "model-00002-of-00002.safetensors",
951
+ "vae.decoder.up_blocks.3.2.attn.to_k.weight": "model-00002-of-00002.safetensors",
952
+ "vae.decoder.up_blocks.3.2.attn.to_out.weight": "model-00002-of-00002.safetensors",
953
+ "vae.decoder.up_blocks.3.2.attn.to_q.weight": "model-00002-of-00002.safetensors",
954
+ "vae.decoder.up_blocks.3.2.attn.to_v.weight": "model-00002-of-00002.safetensors",
955
+ "vae.decoder.up_blocks.3.2.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
956
+ "vae.decoder.up_blocks.3.2.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
957
+ "vae.decoder.up_blocks.3.2.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
958
+ "vae.decoder.up_blocks.3.2.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
959
+ "vae.decoder.up_blocks.3.2.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
960
+ "vae.decoder.up_blocks.3.2.conv_out.norm.bias": "model-00002-of-00002.safetensors",
961
+ "vae.decoder.up_blocks.3.2.conv_out.norm.weight": "model-00002-of-00002.safetensors",
962
+ "vae.decoder.up_blocks.4.0.conv.bias": "model-00002-of-00002.safetensors",
963
+ "vae.decoder.up_blocks.4.0.conv.weight": "model-00002-of-00002.safetensors",
964
+ "vae.decoder.up_blocks.4.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
965
+ "vae.decoder.up_blocks.4.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
966
+ "vae.decoder.up_blocks.4.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
967
+ "vae.decoder.up_blocks.4.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
968
+ "vae.decoder.up_blocks.4.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
969
+ "vae.decoder.up_blocks.4.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
970
+ "vae.decoder.up_blocks.4.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
971
+ "vae.decoder.up_blocks.4.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
972
+ "vae.decoder.up_blocks.4.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
973
+ "vae.decoder.up_blocks.4.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
974
+ "vae.decoder.up_blocks.4.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
975
+ "vae.decoder.up_blocks.4.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
976
+ "vae.decoder.up_blocks.4.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
977
+ "vae.decoder.up_blocks.4.2.attn.norm_out.bias": "model-00002-of-00002.safetensors",
978
+ "vae.decoder.up_blocks.4.2.attn.norm_out.weight": "model-00002-of-00002.safetensors",
979
+ "vae.decoder.up_blocks.4.2.attn.to_k.weight": "model-00002-of-00002.safetensors",
980
+ "vae.decoder.up_blocks.4.2.attn.to_out.weight": "model-00002-of-00002.safetensors",
981
+ "vae.decoder.up_blocks.4.2.attn.to_q.weight": "model-00002-of-00002.safetensors",
982
+ "vae.decoder.up_blocks.4.2.attn.to_v.weight": "model-00002-of-00002.safetensors",
983
+ "vae.decoder.up_blocks.4.2.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
984
+ "vae.decoder.up_blocks.4.2.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
985
+ "vae.decoder.up_blocks.4.2.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
986
+ "vae.decoder.up_blocks.4.2.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
987
+ "vae.decoder.up_blocks.4.2.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
988
+ "vae.decoder.up_blocks.4.2.conv_out.norm.bias": "model-00002-of-00002.safetensors",
989
+ "vae.decoder.up_blocks.4.2.conv_out.norm.weight": "model-00002-of-00002.safetensors",
990
+ "vae.decoder.up_blocks.5.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
991
+ "vae.decoder.up_blocks.5.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
992
+ "vae.decoder.up_blocks.5.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
993
+ "vae.decoder.up_blocks.5.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
994
+ "vae.decoder.up_blocks.5.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
995
+ "vae.decoder.up_blocks.5.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
996
+ "vae.decoder.up_blocks.5.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
997
+ "vae.decoder.up_blocks.5.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
998
+ "vae.decoder.up_blocks.5.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
999
+ "vae.decoder.up_blocks.5.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1000
+ "vae.decoder.up_blocks.5.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1001
+ "vae.decoder.up_blocks.5.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1002
+ "vae.decoder.up_blocks.5.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1003
+ "vae.decoder.up_blocks.5.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1004
+ "vae.decoder.up_blocks.5.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1005
+ "vae.decoder.up_blocks.5.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
1006
+ "vae.decoder.up_blocks.5.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
1007
+ "vae.decoder.up_blocks.5.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
1008
+ "vae.decoder.up_blocks.5.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
1009
+ "vae.decoder.up_blocks.5.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1010
+ "vae.decoder.up_blocks.5.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1011
+ "vae.decoder.up_blocks.5.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1012
+ "vae.decoder.up_blocks.5.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1013
+ "vae.decoder.up_blocks.5.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1014
+ "vae.decoder.up_blocks.5.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1015
+ "vae.decoder.up_blocks.5.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1016
+ "vae.encoder.conv_in.conv.bias": "model-00002-of-00002.safetensors",
1017
+ "vae.encoder.conv_in.conv.weight": "model-00002-of-00002.safetensors",
1018
+ "vae.encoder.conv_out.bias": "model-00002-of-00002.safetensors",
1019
+ "vae.encoder.conv_out.weight": "model-00002-of-00002.safetensors",
1020
+ "vae.encoder.down_blocks.1.0.conv1.bias": "model-00002-of-00002.safetensors",
1021
+ "vae.encoder.down_blocks.1.0.conv1.weight": "model-00002-of-00002.safetensors",
1022
+ "vae.encoder.down_blocks.1.0.conv2.weight": "model-00002-of-00002.safetensors",
1023
+ "vae.encoder.down_blocks.1.0.norm.bias": "model-00002-of-00002.safetensors",
1024
+ "vae.encoder.down_blocks.1.0.norm.weight": "model-00002-of-00002.safetensors",
1025
+ "vae.encoder.down_blocks.1.1.conv1.bias": "model-00002-of-00002.safetensors",
1026
+ "vae.encoder.down_blocks.1.1.conv1.weight": "model-00002-of-00002.safetensors",
1027
+ "vae.encoder.down_blocks.1.1.conv2.weight": "model-00002-of-00002.safetensors",
1028
+ "vae.encoder.down_blocks.1.1.norm.bias": "model-00002-of-00002.safetensors",
1029
+ "vae.encoder.down_blocks.1.1.norm.weight": "model-00002-of-00002.safetensors",
1030
+ "vae.encoder.down_blocks.1.2.conv1.bias": "model-00002-of-00002.safetensors",
1031
+ "vae.encoder.down_blocks.1.2.conv1.weight": "model-00002-of-00002.safetensors",
1032
+ "vae.encoder.down_blocks.1.2.conv2.weight": "model-00002-of-00002.safetensors",
1033
+ "vae.encoder.down_blocks.1.2.norm.bias": "model-00002-of-00002.safetensors",
1034
+ "vae.encoder.down_blocks.1.2.norm.weight": "model-00002-of-00002.safetensors",
1035
+ "vae.encoder.down_blocks.1.3.conv1.bias": "model-00002-of-00002.safetensors",
1036
+ "vae.encoder.down_blocks.1.3.conv1.weight": "model-00002-of-00002.safetensors",
1037
+ "vae.encoder.down_blocks.1.3.conv2.weight": "model-00002-of-00002.safetensors",
1038
+ "vae.encoder.down_blocks.1.3.norm.bias": "model-00002-of-00002.safetensors",
1039
+ "vae.encoder.down_blocks.1.3.norm.weight": "model-00002-of-00002.safetensors",
1040
+ "vae.encoder.down_blocks.1.4.conv.bias": "model-00002-of-00002.safetensors",
1041
+ "vae.encoder.down_blocks.1.4.conv.weight": "model-00002-of-00002.safetensors",
1042
+ "vae.encoder.down_blocks.2.0.conv1.bias": "model-00002-of-00002.safetensors",
1043
+ "vae.encoder.down_blocks.2.0.conv1.weight": "model-00002-of-00002.safetensors",
1044
+ "vae.encoder.down_blocks.2.0.conv2.weight": "model-00002-of-00002.safetensors",
1045
+ "vae.encoder.down_blocks.2.0.norm.bias": "model-00002-of-00002.safetensors",
1046
+ "vae.encoder.down_blocks.2.0.norm.weight": "model-00002-of-00002.safetensors",
1047
+ "vae.encoder.down_blocks.2.1.conv1.bias": "model-00002-of-00002.safetensors",
1048
+ "vae.encoder.down_blocks.2.1.conv1.weight": "model-00002-of-00002.safetensors",
1049
+ "vae.encoder.down_blocks.2.1.conv2.weight": "model-00002-of-00002.safetensors",
1050
+ "vae.encoder.down_blocks.2.1.norm.bias": "model-00002-of-00002.safetensors",
1051
+ "vae.encoder.down_blocks.2.1.norm.weight": "model-00002-of-00002.safetensors",
1052
+ "vae.encoder.down_blocks.2.2.conv1.bias": "model-00002-of-00002.safetensors",
1053
+ "vae.encoder.down_blocks.2.2.conv1.weight": "model-00002-of-00002.safetensors",
1054
+ "vae.encoder.down_blocks.2.2.conv2.weight": "model-00002-of-00002.safetensors",
1055
+ "vae.encoder.down_blocks.2.2.norm.bias": "model-00002-of-00002.safetensors",
1056
+ "vae.encoder.down_blocks.2.2.norm.weight": "model-00002-of-00002.safetensors",
1057
+ "vae.encoder.down_blocks.2.3.conv1.bias": "model-00002-of-00002.safetensors",
1058
+ "vae.encoder.down_blocks.2.3.conv1.weight": "model-00002-of-00002.safetensors",
1059
+ "vae.encoder.down_blocks.2.3.conv2.weight": "model-00002-of-00002.safetensors",
1060
+ "vae.encoder.down_blocks.2.3.norm.bias": "model-00002-of-00002.safetensors",
1061
+ "vae.encoder.down_blocks.2.3.norm.weight": "model-00002-of-00002.safetensors",
1062
+ "vae.encoder.down_blocks.2.4.conv1.bias": "model-00002-of-00002.safetensors",
1063
+ "vae.encoder.down_blocks.2.4.conv1.weight": "model-00002-of-00002.safetensors",
1064
+ "vae.encoder.down_blocks.2.4.conv2.weight": "model-00002-of-00002.safetensors",
1065
+ "vae.encoder.down_blocks.2.4.norm.bias": "model-00002-of-00002.safetensors",
1066
+ "vae.encoder.down_blocks.2.4.norm.weight": "model-00002-of-00002.safetensors",
1067
+ "vae.encoder.down_blocks.2.5.conv1.bias": "model-00002-of-00002.safetensors",
1068
+ "vae.encoder.down_blocks.2.5.conv1.weight": "model-00002-of-00002.safetensors",
1069
+ "vae.encoder.down_blocks.2.5.conv2.weight": "model-00002-of-00002.safetensors",
1070
+ "vae.encoder.down_blocks.2.5.norm.bias": "model-00002-of-00002.safetensors",
1071
+ "vae.encoder.down_blocks.2.5.norm.weight": "model-00002-of-00002.safetensors",
1072
+ "vae.encoder.down_blocks.2.6.conv1.bias": "model-00002-of-00002.safetensors",
1073
+ "vae.encoder.down_blocks.2.6.conv1.weight": "model-00002-of-00002.safetensors",
1074
+ "vae.encoder.down_blocks.2.6.conv2.weight": "model-00002-of-00002.safetensors",
1075
+ "vae.encoder.down_blocks.2.6.norm.bias": "model-00002-of-00002.safetensors",
1076
+ "vae.encoder.down_blocks.2.6.norm.weight": "model-00002-of-00002.safetensors",
1077
+ "vae.encoder.down_blocks.2.7.conv1.bias": "model-00002-of-00002.safetensors",
1078
+ "vae.encoder.down_blocks.2.7.conv1.weight": "model-00002-of-00002.safetensors",
1079
+ "vae.encoder.down_blocks.2.7.conv2.weight": "model-00002-of-00002.safetensors",
1080
+ "vae.encoder.down_blocks.2.7.norm.bias": "model-00002-of-00002.safetensors",
1081
+ "vae.encoder.down_blocks.2.7.norm.weight": "model-00002-of-00002.safetensors",
1082
+ "vae.encoder.down_blocks.2.8.conv.bias": "model-00002-of-00002.safetensors",
1083
+ "vae.encoder.down_blocks.2.8.conv.weight": "model-00002-of-00002.safetensors",
1084
+ "vae.encoder.down_blocks.3.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1085
+ "vae.encoder.down_blocks.3.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1086
+ "vae.encoder.down_blocks.3.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
1087
+ "vae.encoder.down_blocks.3.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
1088
+ "vae.encoder.down_blocks.3.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
1089
+ "vae.encoder.down_blocks.3.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
1090
+ "vae.encoder.down_blocks.3.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1091
+ "vae.encoder.down_blocks.3.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1092
+ "vae.encoder.down_blocks.3.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1093
+ "vae.encoder.down_blocks.3.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1094
+ "vae.encoder.down_blocks.3.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1095
+ "vae.encoder.down_blocks.3.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1096
+ "vae.encoder.down_blocks.3.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1097
+ "vae.encoder.down_blocks.3.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1098
+ "vae.encoder.down_blocks.3.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1099
+ "vae.encoder.down_blocks.3.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
1100
+ "vae.encoder.down_blocks.3.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
1101
+ "vae.encoder.down_blocks.3.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
1102
+ "vae.encoder.down_blocks.3.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
1103
+ "vae.encoder.down_blocks.3.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1104
+ "vae.encoder.down_blocks.3.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1105
+ "vae.encoder.down_blocks.3.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1106
+ "vae.encoder.down_blocks.3.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1107
+ "vae.encoder.down_blocks.3.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1108
+ "vae.encoder.down_blocks.3.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1109
+ "vae.encoder.down_blocks.3.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1110
+ "vae.encoder.down_blocks.3.2.conv.bias": "model-00002-of-00002.safetensors",
1111
+ "vae.encoder.down_blocks.3.2.conv.weight": "model-00002-of-00002.safetensors",
1112
+ "vae.encoder.down_blocks.4.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1113
+ "vae.encoder.down_blocks.4.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1114
+ "vae.encoder.down_blocks.4.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
1115
+ "vae.encoder.down_blocks.4.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
1116
+ "vae.encoder.down_blocks.4.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
1117
+ "vae.encoder.down_blocks.4.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
1118
+ "vae.encoder.down_blocks.4.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1119
+ "vae.encoder.down_blocks.4.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1120
+ "vae.encoder.down_blocks.4.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1121
+ "vae.encoder.down_blocks.4.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1122
+ "vae.encoder.down_blocks.4.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1123
+ "vae.encoder.down_blocks.4.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1124
+ "vae.encoder.down_blocks.4.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1125
+ "vae.encoder.down_blocks.4.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1126
+ "vae.encoder.down_blocks.4.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1127
+ "vae.encoder.down_blocks.4.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
1128
+ "vae.encoder.down_blocks.4.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
1129
+ "vae.encoder.down_blocks.4.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
1130
+ "vae.encoder.down_blocks.4.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
1131
+ "vae.encoder.down_blocks.4.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1132
+ "vae.encoder.down_blocks.4.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1133
+ "vae.encoder.down_blocks.4.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1134
+ "vae.encoder.down_blocks.4.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1135
+ "vae.encoder.down_blocks.4.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1136
+ "vae.encoder.down_blocks.4.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1137
+ "vae.encoder.down_blocks.4.1.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1138
+ "vae.encoder.down_blocks.4.2.conv.bias": "model-00002-of-00002.safetensors",
1139
+ "vae.encoder.down_blocks.4.2.conv.weight": "model-00002-of-00002.safetensors",
1140
+ "vae.encoder.down_blocks.5.0.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1141
+ "vae.encoder.down_blocks.5.0.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1142
+ "vae.encoder.down_blocks.5.0.attn.to_k.weight": "model-00002-of-00002.safetensors",
1143
+ "vae.encoder.down_blocks.5.0.attn.to_out.weight": "model-00002-of-00002.safetensors",
1144
+ "vae.encoder.down_blocks.5.0.attn.to_q.weight": "model-00002-of-00002.safetensors",
1145
+ "vae.encoder.down_blocks.5.0.attn.to_v.weight": "model-00002-of-00002.safetensors",
1146
+ "vae.encoder.down_blocks.5.0.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1147
+ "vae.encoder.down_blocks.5.0.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1148
+ "vae.encoder.down_blocks.5.0.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1149
+ "vae.encoder.down_blocks.5.0.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1150
+ "vae.encoder.down_blocks.5.0.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1151
+ "vae.encoder.down_blocks.5.0.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1152
+ "vae.encoder.down_blocks.5.0.conv_out.norm.weight": "model-00002-of-00002.safetensors",
1153
+ "vae.encoder.down_blocks.5.1.attn.norm_out.bias": "model-00002-of-00002.safetensors",
1154
+ "vae.encoder.down_blocks.5.1.attn.norm_out.weight": "model-00002-of-00002.safetensors",
1155
+ "vae.encoder.down_blocks.5.1.attn.to_k.weight": "model-00002-of-00002.safetensors",
1156
+ "vae.encoder.down_blocks.5.1.attn.to_out.weight": "model-00002-of-00002.safetensors",
1157
+ "vae.encoder.down_blocks.5.1.attn.to_q.weight": "model-00002-of-00002.safetensors",
1158
+ "vae.encoder.down_blocks.5.1.attn.to_v.weight": "model-00002-of-00002.safetensors",
1159
+ "vae.encoder.down_blocks.5.1.conv_out.conv_depth.bias": "model-00002-of-00002.safetensors",
1160
+ "vae.encoder.down_blocks.5.1.conv_out.conv_depth.weight": "model-00002-of-00002.safetensors",
1161
+ "vae.encoder.down_blocks.5.1.conv_out.conv_inverted.bias": "model-00002-of-00002.safetensors",
1162
+ "vae.encoder.down_blocks.5.1.conv_out.conv_inverted.weight": "model-00002-of-00002.safetensors",
1163
+ "vae.encoder.down_blocks.5.1.conv_out.conv_point.weight": "model-00002-of-00002.safetensors",
1164
+ "vae.encoder.down_blocks.5.1.conv_out.norm.bias": "model-00002-of-00002.safetensors",
1165
+ "vae.encoder.down_blocks.5.1.conv_out.norm.weight": "model-00002-of-00002.safetensors"
1166
+ }
1167
+ }
checkpoint-270000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a14d1ecde304589e745680795d692d2ab4ed28aeeea9704e8c08936a8328bb
3
+ size 11384525794
checkpoint-270000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7004241aae4fb8ea8ba24c735fb54a7e2a106fd1c5d77420c938f3c0c128c2b
3
+ size 16389
checkpoint-270000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01be0bff946988f0d9a1513b29368f0bdde01c143fd665e09f47f267e696af1
3
+ size 16389
checkpoint-270000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9020e4c282830c7cad21064456025dc4ecb127fcba4fac677267efd8c6448a1f
3
+ size 16389
checkpoint-270000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b36f0de044a6b8e1b2f5d6d79d7e66c6f9910503b3da0fdc3ff2bf2feaf3047d
3
+ size 16389
checkpoint-270000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53382b2363bf2fe61b13f7ebfe8ddeed2131692691c34ecdd732896492c47a35
3
+ size 16389
checkpoint-270000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:505c9c24c5ef18c1b2a9294b986ad484af902da3bceaa7b7482b818057e50dd5
3
+ size 16389
checkpoint-270000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016af5eb130042208ffebd52fd442daa60a0202c964ba3125800aa6d9e0059b7
3
+ size 16389
checkpoint-270000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62611a863d8fee26a92fc6e3631a897ca202a2dae4838788fe8375c4e7afc0aa
3
+ size 16389
checkpoint-270000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f652f890c71a4dc2e181c2cc1c1d53a66d8328ade04663ab39871349178b0e0
3
+ size 1465
checkpoint-270000/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71cc8cb9e841727410f7aca9e339b2fe92120015f3e6a16531523d55225b2c3e
3
+ size 41361938
checkpoint-270000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:901f4e3ae13ff83ae98e446ce35e228ac210a5ae0be9bddb408cbb5662d5dbb5
3
+ size 6417