OfficerChul commited on
Commit
2a98ab1
·
verified ·
1 Parent(s): 2747365

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,69 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: InfiX-ai/InfiGUI-G1-3B
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft
18
+
19
+ This model is a fine-tuned version of [InfiX-ai/InfiGUI-G1-3B](https://huggingface.co/InfiX-ai/InfiGUI-G1-3B) on the and_ctrl_skt dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1624
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 48
47
+ - total_train_batch_size: 768
48
+ - total_eval_batch_size: 4
49
+ - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 5.0
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:------:|:----:|:---------------:|
58
+ | 0.2532 | 1.1120 | 100 | 0.2310 |
59
+ | 0.1713 | 2.2239 | 200 | 0.1800 |
60
+ | 0.1178 | 3.3359 | 300 | 0.1559 |
61
+ | 0.0765 | 4.4479 | 400 | 0.1624 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.56.1
67
+ - Pytorch 2.5.0a0+b465a5843b.nv24.09
68
+ - Datasets 3.0.1
69
+ - Tokenizers 0.22.1
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.1624332219362259,
4
+ "eval_runtime": 336.6612,
5
+ "eval_samples_per_second": 10.726,
6
+ "eval_steps_per_second": 2.682,
7
+ "total_flos": 1141497040732160.0,
8
+ "train_loss": 0.24183495627509224,
9
+ "train_runtime": 30070.9864,
10
+ "train_samples_per_second": 11.405,
11
+ "train_steps_per_second": 0.015
12
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 36,
18
+ "num_key_value_heads": 2,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "text_config": {
33
+ "architectures": [
34
+ "Qwen2_5_VLForConditionalGeneration"
35
+ ],
36
+ "attention_dropout": 0.0,
37
+ "dtype": "float32",
38
+ "eos_token_id": 151645,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 2048,
41
+ "image_token_id": null,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 11008,
44
+ "layer_types": [
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention"
81
+ ],
82
+ "max_position_embeddings": 128000,
83
+ "max_window_layers": 70,
84
+ "model_type": "qwen2_5_vl_text",
85
+ "num_attention_heads": 16,
86
+ "num_hidden_layers": 36,
87
+ "num_key_value_heads": 2,
88
+ "pad_token_id": 151643,
89
+ "rms_norm_eps": 1e-06,
90
+ "rope_scaling": {
91
+ "mrope_section": [
92
+ 16,
93
+ 24,
94
+ 24
95
+ ],
96
+ "rope_type": "default",
97
+ "type": "default"
98
+ },
99
+ "rope_theta": 1000000.0,
100
+ "sliding_window": null,
101
+ "tie_word_embeddings": true,
102
+ "use_cache": false,
103
+ "use_sliding_window": false,
104
+ "video_token_id": null,
105
+ "vision_end_token_id": 151653,
106
+ "vision_start_token_id": 151652,
107
+ "vision_token_id": 151654,
108
+ "vocab_size": 151936
109
+ },
110
+ "transformers_version": "4.56.1",
111
+ "use_cache": false,
112
+ "use_sliding_window": false,
113
+ "video_token_id": 151656,
114
+ "vision_config": {
115
+ "depth": 32,
116
+ "dtype": "float32",
117
+ "fullatt_block_indexes": [
118
+ 7,
119
+ 15,
120
+ 23,
121
+ 31
122
+ ],
123
+ "hidden_act": "silu",
124
+ "hidden_size": 1280,
125
+ "in_channels": 3,
126
+ "in_chans": 3,
127
+ "initializer_range": 0.02,
128
+ "intermediate_size": 3420,
129
+ "model_type": "qwen2_5_vl",
130
+ "num_heads": 16,
131
+ "out_hidden_size": 2048,
132
+ "patch_size": 14,
133
+ "spatial_merge_size": 2,
134
+ "spatial_patch_size": 14,
135
+ "temporal_patch_size": 2,
136
+ "tokens_per_second": 2,
137
+ "window_size": 112
138
+ },
139
+ "vision_end_token_id": 151653,
140
+ "vision_start_token_id": 151652,
141
+ "vision_token_id": 151654,
142
+ "vocab_size": 151936
143
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.1624332219362259,
4
+ "eval_runtime": 336.6612,
5
+ "eval_samples_per_second": 10.726,
6
+ "eval_steps_per_second": 2.682
7
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.05,
9
+ "temperature": 0.1,
10
+ "top_k": 1,
11
+ "top_p": 0.001,
12
+ "transformers_version": "4.56.1"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65eba998e9464df4311c6e848d288efc7f821070643876ff8770e2ce9fe4b704
3
+ size 4997750760
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709ba24bd4649889aa92000ec971b37ffea59391357d73d731bc7dcac5e742e9
3
+ size 2511587184
model.safetensors.index.json ADDED
@@ -0,0 +1,832 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 3754622976,
4
+ "total_size": 7509245952
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
379
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
391
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
403
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
415
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
425
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
426
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
427
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
437
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
439
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.norm.weight": "model-00002-of-00002.safetensors",
441
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
442
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
443
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
444
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
445
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
446
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
447
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
448
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
449
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
450
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
451
+ "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
452
+ "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
453
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
454
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
455
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
456
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
457
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
458
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
459
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
460
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
461
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
462
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
463
+ "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
464
+ "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
465
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
466
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
467
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
468
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
469
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
470
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
471
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
472
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
473
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
474
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
475
+ "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
476
+ "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
477
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
478
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
479
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
480
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
481
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
482
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
483
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
484
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
485
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
486
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
487
+ "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
488
+ "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
489
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
490
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
491
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
492
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
493
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
494
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
495
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
496
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
497
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
498
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
499
+ "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
500
+ "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
501
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
502
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
503
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
504
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
505
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
506
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
507
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
508
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
509
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
510
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
511
+ "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
512
+ "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
513
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
514
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
515
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
516
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
517
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
518
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
519
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
520
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
521
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
522
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
523
+ "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
524
+ "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
525
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
526
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
527
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
528
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
529
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
530
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
531
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
532
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
533
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
534
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
535
+ "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
536
+ "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
537
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
538
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
539
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
540
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
541
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
542
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
543
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
544
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
545
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
546
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
547
+ "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
548
+ "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
549
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
550
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
551
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
552
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
553
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
554
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
555
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
556
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
557
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
558
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
559
+ "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
560
+ "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
561
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
562
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
563
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
564
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
565
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
566
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
567
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
568
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
569
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
570
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
571
+ "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
572
+ "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
573
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
574
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
575
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
576
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
577
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
578
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
579
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
580
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
581
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
582
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
583
+ "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
584
+ "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
585
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
586
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
587
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
588
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
589
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
590
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
591
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
592
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
593
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
594
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
595
+ "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
596
+ "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
597
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
598
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
599
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
600
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
601
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
602
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
603
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
604
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
605
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
606
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
607
+ "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
608
+ "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
609
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
610
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
611
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
612
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
613
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
614
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
615
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
616
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
617
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
618
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
619
+ "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
620
+ "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
621
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
622
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
623
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
624
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
625
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
626
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
627
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
628
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
629
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
630
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
631
+ "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
632
+ "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
633
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
634
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
635
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
636
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
637
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
638
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
639
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
640
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
641
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
642
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
643
+ "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
644
+ "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
645
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
646
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
647
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
648
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
649
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
650
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
651
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
652
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
653
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
654
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
655
+ "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
656
+ "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
657
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
658
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
659
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
660
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
661
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
662
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
663
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
664
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
665
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
666
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
667
+ "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
668
+ "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
669
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
670
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
671
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
672
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
673
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
674
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
675
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
676
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
677
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
678
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
679
+ "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
680
+ "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
681
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
682
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
683
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
684
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
685
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
686
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
687
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
688
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
689
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
690
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
691
+ "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
692
+ "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
693
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
694
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
695
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
696
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
697
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
698
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
699
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
700
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
701
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
702
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
703
+ "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
704
+ "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
705
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
706
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
707
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
708
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
709
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
710
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
711
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
712
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
713
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
714
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
715
+ "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
716
+ "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
717
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
718
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
719
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
720
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
721
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
722
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
723
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
724
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
725
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
726
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
727
+ "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
728
+ "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
729
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
730
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
731
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
732
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
733
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
734
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
735
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
736
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
737
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
738
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
739
+ "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
740
+ "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
741
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
742
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
743
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
744
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
745
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
746
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
747
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
748
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
749
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
750
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
751
+ "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
752
+ "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
753
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
754
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
755
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
756
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
757
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
758
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
759
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
760
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
761
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
762
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
763
+ "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
764
+ "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
765
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
766
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
767
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
768
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
769
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
770
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
771
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
772
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
773
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
774
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
775
+ "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
776
+ "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
777
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
778
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
779
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
780
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
781
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
782
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
783
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
784
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
785
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
786
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
787
+ "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
788
+ "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
789
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
790
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
791
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
792
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
793
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
794
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
795
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
796
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
797
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
798
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
799
+ "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
800
+ "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
801
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
802
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
803
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
804
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
805
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
806
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
807
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
808
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
809
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
810
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
811
+ "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
812
+ "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
813
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
814
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
815
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
816
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
817
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
818
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
819
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
820
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
821
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
822
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
823
+ "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
824
+ "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
825
+ "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
826
+ "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
827
+ "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
828
+ "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
829
+ "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
830
+ "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
831
+ }
832
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessorFast",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "input_data_format": null,
24
+ "max_pixels": 12845056,
25
+ "merge_size": 2,
26
+ "min_pixels": 3136,
27
+ "patch_size": 14,
28
+ "processor_class": "Qwen2_5_VLProcessor",
29
+ "resample": 3,
30
+ "rescale_factor": 0.00392156862745098,
31
+ "return_tensors": null,
32
+ "size": {
33
+ "longest_edge": 12845056,
34
+ "shortest_edge": 3136
35
+ },
36
+ "temporal_patch_size": 2
37
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "processor_class": "Qwen2_5_VLProcessor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 1141497040732160.0,
4
+ "train_loss": 0.24183495627509224,
5
+ "train_runtime": 30070.9864,
6
+ "train_samples_per_second": 11.405,
7
+ "train_steps_per_second": 0.015
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 450, "loss": 2.8571, "lr": 4.000000000000001e-06, "epoch": 0.11196641007697691, "percentage": 2.22, "elapsed_time": "0:10:32", "remaining_time": "7:43:35"}
2
+ {"current_steps": 20, "total_steps": 450, "loss": 0.6148, "lr": 8.444444444444446e-06, "epoch": 0.22393282015395383, "percentage": 4.44, "elapsed_time": "0:21:00", "remaining_time": "7:31:39"}
3
+ {"current_steps": 30, "total_steps": 450, "loss": 0.3928, "lr": 1.288888888888889e-05, "epoch": 0.3358992302309307, "percentage": 6.67, "elapsed_time": "0:31:32", "remaining_time": "7:21:39"}
4
+ {"current_steps": 40, "total_steps": 450, "loss": 0.3458, "lr": 1.7333333333333336e-05, "epoch": 0.44786564030790765, "percentage": 8.89, "elapsed_time": "0:42:07", "remaining_time": "7:11:42"}
5
+ {"current_steps": 50, "total_steps": 450, "loss": 0.3267, "lr": 1.9995186678809513e-05, "epoch": 0.5598320503848845, "percentage": 11.11, "elapsed_time": "0:52:40", "remaining_time": "7:01:24"}
6
+ {"current_steps": 60, "total_steps": 450, "loss": 0.3158, "lr": 1.9941090015469614e-05, "epoch": 0.6717984604618614, "percentage": 13.33, "elapsed_time": "1:03:14", "remaining_time": "6:51:02"}
7
+ {"current_steps": 70, "total_steps": 450, "loss": 0.3016, "lr": 1.9827206467064133e-05, "epoch": 0.7837648705388384, "percentage": 15.56, "elapsed_time": "1:13:47", "remaining_time": "6:40:35"}
8
+ {"current_steps": 80, "total_steps": 450, "loss": 0.278, "lr": 1.9654220942653223e-05, "epoch": 0.8957312806158153, "percentage": 17.78, "elapsed_time": "1:24:23", "remaining_time": "6:30:18"}
9
+ {"current_steps": 90, "total_steps": 450, "loss": 0.2639, "lr": 1.9423173797534924e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "1:34:15", "remaining_time": "6:17:02"}
10
+ {"current_steps": 100, "total_steps": 450, "loss": 0.2532, "lr": 1.913545457642601e-05, "epoch": 1.1119664100769768, "percentage": 22.22, "elapsed_time": "1:44:53", "remaining_time": "6:07:07"}
11
+ {"current_steps": 100, "total_steps": 450, "eval_loss": 0.2309780865907669, "epoch": 1.1119664100769768, "percentage": 22.22, "elapsed_time": "1:50:28", "remaining_time": "6:26:40"}
12
+ {"current_steps": 110, "total_steps": 450, "loss": 0.2366, "lr": 1.8792793656576544e-05, "epoch": 1.2239328201539539, "percentage": 24.44, "elapsed_time": "2:01:41", "remaining_time": "6:16:07"}
13
+ {"current_steps": 120, "total_steps": 450, "loss": 0.2316, "lr": 1.83972518410775e-05, "epoch": 1.3358992302309307, "percentage": 26.67, "elapsed_time": "2:12:20", "remaining_time": "6:03:57"}
14
+ {"current_steps": 130, "total_steps": 450, "loss": 0.2216, "lr": 1.795120796494848e-05, "epoch": 1.4478656403079078, "percentage": 28.89, "elapsed_time": "2:22:57", "remaining_time": "5:51:54"}
15
+ {"current_steps": 140, "total_steps": 450, "loss": 0.2155, "lr": 1.7457344588544018e-05, "epoch": 1.5598320503848844, "percentage": 31.11, "elapsed_time": "2:33:35", "remaining_time": "5:40:06"}
16
+ {"current_steps": 150, "total_steps": 450, "loss": 0.2122, "lr": 1.691863186431996e-05, "epoch": 1.6717984604618614, "percentage": 33.33, "elapsed_time": "2:44:14", "remaining_time": "5:28:28"}
17
+ {"current_steps": 160, "total_steps": 450, "loss": 0.2059, "lr": 1.63383096739871e-05, "epoch": 1.7837648705388385, "percentage": 35.56, "elapsed_time": "2:54:50", "remaining_time": "5:16:54"}
18
+ {"current_steps": 170, "total_steps": 450, "loss": 0.2034, "lr": 1.5719868143481385e-05, "epoch": 1.8957312806158153, "percentage": 37.78, "elapsed_time": "3:05:28", "remaining_time": "5:05:29"}
19
+ {"current_steps": 180, "total_steps": 450, "loss": 0.1995, "lr": 1.5067026652935823e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "3:15:22", "remaining_time": "4:53:03"}
20
+ {"current_steps": 190, "total_steps": 450, "loss": 0.1764, "lr": 1.4383711467890776e-05, "epoch": 2.111966410076977, "percentage": 42.22, "elapsed_time": "3:26:02", "remaining_time": "4:41:56"}
21
+ {"current_steps": 200, "total_steps": 450, "loss": 0.1713, "lr": 1.3674032126270982e-05, "epoch": 2.2239328201539537, "percentage": 44.44, "elapsed_time": "3:36:41", "remaining_time": "4:30:52"}
22
+ {"current_steps": 200, "total_steps": 450, "eval_loss": 0.18000730872154236, "epoch": 2.2239328201539537, "percentage": 44.44, "elapsed_time": "3:42:18", "remaining_time": "4:37:53"}
23
+ {"current_steps": 210, "total_steps": 450, "loss": 0.1671, "lr": 1.2942256723140951e-05, "epoch": 2.3358992302309307, "percentage": 46.67, "elapsed_time": "3:53:31", "remaining_time": "4:26:53"}
24
+ {"current_steps": 220, "total_steps": 450, "loss": 0.1703, "lr": 1.2192786241879033e-05, "epoch": 2.4478656403079078, "percentage": 48.89, "elapsed_time": "4:04:10", "remaining_time": "4:15:16"}
25
+ {"current_steps": 230, "total_steps": 450, "loss": 0.1642, "lr": 1.1430128086145542e-05, "epoch": 2.5598320503848844, "percentage": 51.11, "elapsed_time": "4:14:49", "remaining_time": "4:03:45"}
26
+ {"current_steps": 240, "total_steps": 450, "loss": 0.1553, "lr": 1.0658868971826785e-05, "epoch": 2.6717984604618614, "percentage": 53.33, "elapsed_time": "4:25:28", "remaining_time": "3:52:17"}
27
+ {"current_steps": 250, "total_steps": 450, "loss": 0.1616, "lr": 9.883647341986032e-06, "epoch": 2.7837648705388385, "percentage": 55.56, "elapsed_time": "4:36:07", "remaining_time": "3:40:53"}
28
+ {"current_steps": 260, "total_steps": 450, "loss": 0.157, "lr": 9.109125470721141e-06, "epoch": 2.8957312806158155, "percentage": 57.78, "elapsed_time": "4:46:45", "remaining_time": "3:29:33"}
29
+ {"current_steps": 270, "total_steps": 450, "loss": 0.1528, "lr": 8.339961423699563e-06, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "4:56:41", "remaining_time": "3:17:47"}
30
+ {"current_steps": 280, "total_steps": 450, "loss": 0.1249, "lr": 7.580781044003324e-06, "epoch": 3.111966410076977, "percentage": 62.22, "elapsed_time": "5:07:25", "remaining_time": "3:06:39"}
31
+ {"current_steps": 290, "total_steps": 450, "loss": 0.1168, "lr": 6.836150131764434e-06, "epoch": 3.2239328201539537, "percentage": 64.44, "elapsed_time": "5:18:07", "remaining_time": "2:55:31"}
32
+ {"current_steps": 300, "total_steps": 450, "loss": 0.1178, "lr": 6.110546984905661e-06, "epoch": 3.3358992302309307, "percentage": 66.67, "elapsed_time": "5:28:51", "remaining_time": "2:44:25"}
33
+ {"current_steps": 300, "total_steps": 450, "eval_loss": 0.15590140223503113, "epoch": 3.3358992302309307, "percentage": 66.67, "elapsed_time": "5:34:27", "remaining_time": "2:47:13"}
34
+ {"current_steps": 310, "total_steps": 450, "loss": 0.1208, "lr": 5.4083354661298816e-06, "epoch": 3.4478656403079078, "percentage": 68.89, "elapsed_time": "5:45:41", "remaining_time": "2:36:07"}
35
+ {"current_steps": 320, "total_steps": 450, "loss": 0.1144, "lr": 4.733738758136327e-06, "epoch": 3.5598320503848844, "percentage": 71.11, "elapsed_time": "5:56:22", "remaining_time": "2:24:46"}
36
+ {"current_steps": 330, "total_steps": 450, "loss": 0.1156, "lr": 4.090813964902889e-06, "epoch": 3.6717984604618614, "percentage": 73.33, "elapsed_time": "6:07:04", "remaining_time": "2:13:28"}
37
+ {"current_steps": 340, "total_steps": 450, "loss": 0.1132, "lr": 3.483427711785449e-06, "epoch": 3.7837648705388385, "percentage": 75.56, "elapsed_time": "6:17:45", "remaining_time": "2:02:12"}
38
+ {"current_steps": 350, "total_steps": 450, "loss": 0.1116, "lr": 2.9152328911780027e-06, "epoch": 3.8957312806158155, "percentage": 77.78, "elapsed_time": "6:28:28", "remaining_time": "1:50:59"}
39
+ {"current_steps": 360, "total_steps": 450, "loss": 0.1115, "lr": 2.3896466935879957e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "6:38:27", "remaining_time": "1:39:36"}
40
+ {"current_steps": 370, "total_steps": 450, "loss": 0.0792, "lr": 1.9098300562505266e-06, "epoch": 4.111966410076977, "percentage": 82.22, "elapsed_time": "6:49:12", "remaining_time": "1:28:28"}
41
+ {"current_steps": 380, "total_steps": 450, "loss": 0.0739, "lr": 1.4786686528798878e-06, "epoch": 4.223932820153954, "percentage": 84.44, "elapsed_time": "6:59:56", "remaining_time": "1:17:21"}
42
+ {"current_steps": 390, "total_steps": 450, "loss": 0.0777, "lr": 1.0987555388883042e-06, "epoch": 4.335899230230931, "percentage": 86.67, "elapsed_time": "7:10:39", "remaining_time": "1:06:15"}
43
+ {"current_steps": 400, "total_steps": 450, "loss": 0.0765, "lr": 7.723755564455771e-07, "epoch": 4.447865640307907, "percentage": 88.89, "elapsed_time": "7:21:23", "remaining_time": "0:55:10"}
44
+ {"current_steps": 400, "total_steps": 450, "eval_loss": 0.16239598393440247, "epoch": 4.447865640307907, "percentage": 88.89, "elapsed_time": "7:26:59", "remaining_time": "0:55:52"}
45
+ {"current_steps": 410, "total_steps": 450, "loss": 0.0784, "lr": 5.014915931694253e-07, "epoch": 4.559832050384885, "percentage": 91.11, "elapsed_time": "7:38:19", "remaining_time": "0:44:42"}
46
+ {"current_steps": 420, "total_steps": 450, "loss": 0.0774, "lr": 2.877327770883964e-07, "epoch": 4.671798460461861, "percentage": 93.33, "elapsed_time": "7:49:05", "remaining_time": "0:33:30"}
47
+ {"current_steps": 430, "total_steps": 450, "loss": 0.0736, "lr": 1.323846788742078e-07, "epoch": 4.783764870538838, "percentage": 95.56, "elapsed_time": "7:59:49", "remaining_time": "0:22:19"}
48
+ {"current_steps": 440, "total_steps": 450, "loss": 0.0748, "lr": 3.6381580268463056e-08, "epoch": 4.8957312806158155, "percentage": 97.78, "elapsed_time": "8:10:35", "remaining_time": "0:11:08"}
49
+ {"current_steps": 450, "total_steps": 450, "loss": 0.0727, "lr": 3.008552023242572e-10, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "8:20:37", "remaining_time": "0:00:00"}
50
+ {"current_steps": 450, "total_steps": 450, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "8:21:09", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,390 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 100,
7
+ "global_step": 450,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.11196641007697691,
14
+ "grad_norm": 21.06309415699912,
15
+ "learning_rate": 4.000000000000001e-06,
16
+ "loss": 2.8571,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.22393282015395383,
21
+ "grad_norm": 1.9727286004327564,
22
+ "learning_rate": 8.444444444444446e-06,
23
+ "loss": 0.6148,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.3358992302309307,
28
+ "grad_norm": 2.2884377083477645,
29
+ "learning_rate": 1.288888888888889e-05,
30
+ "loss": 0.3928,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.44786564030790765,
35
+ "grad_norm": 1.647085854397205,
36
+ "learning_rate": 1.7333333333333336e-05,
37
+ "loss": 0.3458,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.5598320503848845,
42
+ "grad_norm": 2.329816835595036,
43
+ "learning_rate": 1.9995186678809513e-05,
44
+ "loss": 0.3267,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.6717984604618614,
49
+ "grad_norm": 1.519218251845277,
50
+ "learning_rate": 1.9941090015469614e-05,
51
+ "loss": 0.3158,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.7837648705388384,
56
+ "grad_norm": 1.3244908123467292,
57
+ "learning_rate": 1.9827206467064133e-05,
58
+ "loss": 0.3016,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.8957312806158153,
63
+ "grad_norm": 1.0638147560775397,
64
+ "learning_rate": 1.9654220942653223e-05,
65
+ "loss": 0.278,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 1.0,
70
+ "grad_norm": 1.3750398954831957,
71
+ "learning_rate": 1.9423173797534924e-05,
72
+ "loss": 0.2639,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 1.1119664100769768,
77
+ "grad_norm": 1.4059952043975563,
78
+ "learning_rate": 1.913545457642601e-05,
79
+ "loss": 0.2532,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 1.1119664100769768,
84
+ "eval_loss": 0.2309780865907669,
85
+ "eval_runtime": 334.81,
86
+ "eval_samples_per_second": 10.785,
87
+ "eval_steps_per_second": 2.697,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 1.2239328201539539,
92
+ "grad_norm": 0.7770380776412505,
93
+ "learning_rate": 1.8792793656576544e-05,
94
+ "loss": 0.2366,
95
+ "step": 110
96
+ },
97
+ {
98
+ "epoch": 1.3358992302309307,
99
+ "grad_norm": 1.053613780680287,
100
+ "learning_rate": 1.83972518410775e-05,
101
+ "loss": 0.2316,
102
+ "step": 120
103
+ },
104
+ {
105
+ "epoch": 1.4478656403079078,
106
+ "grad_norm": 0.8850308205683671,
107
+ "learning_rate": 1.795120796494848e-05,
108
+ "loss": 0.2216,
109
+ "step": 130
110
+ },
111
+ {
112
+ "epoch": 1.5598320503848844,
113
+ "grad_norm": 1.080177617549634,
114
+ "learning_rate": 1.7457344588544018e-05,
115
+ "loss": 0.2155,
116
+ "step": 140
117
+ },
118
+ {
119
+ "epoch": 1.6717984604618614,
120
+ "grad_norm": 0.8218548086924884,
121
+ "learning_rate": 1.691863186431996e-05,
122
+ "loss": 0.2122,
123
+ "step": 150
124
+ },
125
+ {
126
+ "epoch": 1.7837648705388385,
127
+ "grad_norm": 0.6988372786589893,
128
+ "learning_rate": 1.63383096739871e-05,
129
+ "loss": 0.2059,
130
+ "step": 160
131
+ },
132
+ {
133
+ "epoch": 1.8957312806158153,
134
+ "grad_norm": 0.7684849910572107,
135
+ "learning_rate": 1.5719868143481385e-05,
136
+ "loss": 0.2034,
137
+ "step": 170
138
+ },
139
+ {
140
+ "epoch": 2.0,
141
+ "grad_norm": 1.2808833317754085,
142
+ "learning_rate": 1.5067026652935823e-05,
143
+ "loss": 0.1995,
144
+ "step": 180
145
+ },
146
+ {
147
+ "epoch": 2.111966410076977,
148
+ "grad_norm": 0.9108986394736251,
149
+ "learning_rate": 1.4383711467890776e-05,
150
+ "loss": 0.1764,
151
+ "step": 190
152
+ },
153
+ {
154
+ "epoch": 2.2239328201539537,
155
+ "grad_norm": 1.0633553433425496,
156
+ "learning_rate": 1.3674032126270982e-05,
157
+ "loss": 0.1713,
158
+ "step": 200
159
+ },
160
+ {
161
+ "epoch": 2.2239328201539537,
162
+ "eval_loss": 0.18000730872154236,
163
+ "eval_runtime": 337.0653,
164
+ "eval_samples_per_second": 10.713,
165
+ "eval_steps_per_second": 2.679,
166
+ "step": 200
167
+ },
168
+ {
169
+ "epoch": 2.3358992302309307,
170
+ "grad_norm": 0.8859214091666336,
171
+ "learning_rate": 1.2942256723140951e-05,
172
+ "loss": 0.1671,
173
+ "step": 210
174
+ },
175
+ {
176
+ "epoch": 2.4478656403079078,
177
+ "grad_norm": 0.849493216288489,
178
+ "learning_rate": 1.2192786241879033e-05,
179
+ "loss": 0.1703,
180
+ "step": 220
181
+ },
182
+ {
183
+ "epoch": 2.5598320503848844,
184
+ "grad_norm": 1.0004480128274726,
185
+ "learning_rate": 1.1430128086145542e-05,
186
+ "loss": 0.1642,
187
+ "step": 230
188
+ },
189
+ {
190
+ "epoch": 2.6717984604618614,
191
+ "grad_norm": 0.9096432098561809,
192
+ "learning_rate": 1.0658868971826785e-05,
193
+ "loss": 0.1553,
194
+ "step": 240
195
+ },
196
+ {
197
+ "epoch": 2.7837648705388385,
198
+ "grad_norm": 0.7475626808919502,
199
+ "learning_rate": 9.883647341986032e-06,
200
+ "loss": 0.1616,
201
+ "step": 250
202
+ },
203
+ {
204
+ "epoch": 2.8957312806158155,
205
+ "grad_norm": 0.7289602464956204,
206
+ "learning_rate": 9.109125470721141e-06,
207
+ "loss": 0.157,
208
+ "step": 260
209
+ },
210
+ {
211
+ "epoch": 3.0,
212
+ "grad_norm": 0.9343429127547538,
213
+ "learning_rate": 8.339961423699563e-06,
214
+ "loss": 0.1528,
215
+ "step": 270
216
+ },
217
+ {
218
+ "epoch": 3.111966410076977,
219
+ "grad_norm": 0.8272491815261758,
220
+ "learning_rate": 7.580781044003324e-06,
221
+ "loss": 0.1249,
222
+ "step": 280
223
+ },
224
+ {
225
+ "epoch": 3.2239328201539537,
226
+ "grad_norm": 0.8785316150577709,
227
+ "learning_rate": 6.836150131764434e-06,
228
+ "loss": 0.1168,
229
+ "step": 290
230
+ },
231
+ {
232
+ "epoch": 3.3358992302309307,
233
+ "grad_norm": 0.8757974207894819,
234
+ "learning_rate": 6.110546984905661e-06,
235
+ "loss": 0.1178,
236
+ "step": 300
237
+ },
238
+ {
239
+ "epoch": 3.3358992302309307,
240
+ "eval_loss": 0.15590140223503113,
241
+ "eval_runtime": 335.9835,
242
+ "eval_samples_per_second": 10.748,
243
+ "eval_steps_per_second": 2.688,
244
+ "step": 300
245
+ },
246
+ {
247
+ "epoch": 3.4478656403079078,
248
+ "grad_norm": 0.8970654870881085,
249
+ "learning_rate": 5.4083354661298816e-06,
250
+ "loss": 0.1208,
251
+ "step": 310
252
+ },
253
+ {
254
+ "epoch": 3.5598320503848844,
255
+ "grad_norm": 0.7754639069886827,
256
+ "learning_rate": 4.733738758136327e-06,
257
+ "loss": 0.1144,
258
+ "step": 320
259
+ },
260
+ {
261
+ "epoch": 3.6717984604618614,
262
+ "grad_norm": 1.892274710129508,
263
+ "learning_rate": 4.090813964902889e-06,
264
+ "loss": 0.1156,
265
+ "step": 330
266
+ },
267
+ {
268
+ "epoch": 3.7837648705388385,
269
+ "grad_norm": 1.2589854864442425,
270
+ "learning_rate": 3.483427711785449e-06,
271
+ "loss": 0.1132,
272
+ "step": 340
273
+ },
274
+ {
275
+ "epoch": 3.8957312806158155,
276
+ "grad_norm": 0.8837972275737342,
277
+ "learning_rate": 2.9152328911780027e-06,
278
+ "loss": 0.1116,
279
+ "step": 350
280
+ },
281
+ {
282
+ "epoch": 4.0,
283
+ "grad_norm": 2.2328227938809153,
284
+ "learning_rate": 2.3896466935879957e-06,
285
+ "loss": 0.1115,
286
+ "step": 360
287
+ },
288
+ {
289
+ "epoch": 4.111966410076977,
290
+ "grad_norm": 0.9921573733470108,
291
+ "learning_rate": 1.9098300562505266e-06,
292
+ "loss": 0.0792,
293
+ "step": 370
294
+ },
295
+ {
296
+ "epoch": 4.223932820153954,
297
+ "grad_norm": 2.590495365853637,
298
+ "learning_rate": 1.4786686528798878e-06,
299
+ "loss": 0.0739,
300
+ "step": 380
301
+ },
302
+ {
303
+ "epoch": 4.335899230230931,
304
+ "grad_norm": 1.172303338637939,
305
+ "learning_rate": 1.0987555388883042e-06,
306
+ "loss": 0.0777,
307
+ "step": 390
308
+ },
309
+ {
310
+ "epoch": 4.447865640307907,
311
+ "grad_norm": 0.9032745376031973,
312
+ "learning_rate": 7.723755564455771e-07,
313
+ "loss": 0.0765,
314
+ "step": 400
315
+ },
316
+ {
317
+ "epoch": 4.447865640307907,
318
+ "eval_loss": 0.16239598393440247,
319
+ "eval_runtime": 335.8645,
320
+ "eval_samples_per_second": 10.751,
321
+ "eval_steps_per_second": 2.689,
322
+ "step": 400
323
+ },
324
+ {
325
+ "epoch": 4.559832050384885,
326
+ "grad_norm": 1.200437444817232,
327
+ "learning_rate": 5.014915931694253e-07,
328
+ "loss": 0.0784,
329
+ "step": 410
330
+ },
331
+ {
332
+ "epoch": 4.671798460461861,
333
+ "grad_norm": 2.214432160562882,
334
+ "learning_rate": 2.877327770883964e-07,
335
+ "loss": 0.0774,
336
+ "step": 420
337
+ },
338
+ {
339
+ "epoch": 4.783764870538838,
340
+ "grad_norm": 0.7916736334089312,
341
+ "learning_rate": 1.323846788742078e-07,
342
+ "loss": 0.0736,
343
+ "step": 430
344
+ },
345
+ {
346
+ "epoch": 4.8957312806158155,
347
+ "grad_norm": 0.8181788452191515,
348
+ "learning_rate": 3.6381580268463056e-08,
349
+ "loss": 0.0748,
350
+ "step": 440
351
+ },
352
+ {
353
+ "epoch": 5.0,
354
+ "grad_norm": 8.445524032141444,
355
+ "learning_rate": 3.008552023242572e-10,
356
+ "loss": 0.0727,
357
+ "step": 450
358
+ },
359
+ {
360
+ "epoch": 5.0,
361
+ "step": 450,
362
+ "total_flos": 1141497040732160.0,
363
+ "train_loss": 0.24183495627509224,
364
+ "train_runtime": 30070.9864,
365
+ "train_samples_per_second": 11.405,
366
+ "train_steps_per_second": 0.015
367
+ }
368
+ ],
369
+ "logging_steps": 10,
370
+ "max_steps": 450,
371
+ "num_input_tokens_seen": 0,
372
+ "num_train_epochs": 5,
373
+ "save_steps": 100,
374
+ "stateful_callbacks": {
375
+ "TrainerControl": {
376
+ "args": {
377
+ "should_epoch_stop": false,
378
+ "should_evaluate": false,
379
+ "should_log": false,
380
+ "should_save": true,
381
+ "should_training_stop": true
382
+ },
383
+ "attributes": {}
384
+ }
385
+ },
386
+ "total_flos": 1141497040732160.0,
387
+ "train_batch_size": 4,
388
+ "trial_name": null,
389
+ "trial_params": null
390
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd7158fcca64e842d0d1142f9bfa2df5b21f3125b651ac85671d978c931b039
3
+ size 7480
training_eval_loss.png ADDED
training_loss.png ADDED
video_preprocessor_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_frames": 768,
26
+ "max_pixels": 12845056,
27
+ "merge_size": 2,
28
+ "min_frames": 4,
29
+ "min_pixels": 3136,
30
+ "num_frames": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2_5_VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "return_metadata": false,
36
+ "size": {
37
+ "longest_edge": 12845056,
38
+ "shortest_edge": 3136
39
+ },
40
+ "size_divisor": null,
41
+ "temporal_patch_size": 2,
42
+ "video_metadata": null,
43
+ "video_processor_type": "Qwen2VLVideoProcessor"
44
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff