redmoe-ai-v1 commited on
Commit
b4e9f55
·
verified ·
1 Parent(s): 9f8a68c

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. config.json +91 -0
  2. model-00001-of-00316.safetensors +3 -0
  3. model-00002-of-00316.safetensors +3 -0
  4. model-00003-of-00316.safetensors +3 -0
  5. model-00004-of-00316.safetensors +3 -0
  6. model-00005-of-00316.safetensors +3 -0
  7. model-00006-of-00316.safetensors +3 -0
  8. model-00007-of-00316.safetensors +3 -0
  9. model-00008-of-00316.safetensors +3 -0
  10. model-00009-of-00316.safetensors +3 -0
  11. model-00010-of-00316.safetensors +3 -0
  12. model-00011-of-00316.safetensors +3 -0
  13. model-00012-of-00316.safetensors +3 -0
  14. model-00013-of-00316.safetensors +3 -0
  15. model-00014-of-00316.safetensors +3 -0
  16. model-00015-of-00316.safetensors +3 -0
  17. model-00016-of-00316.safetensors +3 -0
  18. model-00017-of-00316.safetensors +3 -0
  19. model-00018-of-00316.safetensors +3 -0
  20. model-00019-of-00316.safetensors +3 -0
  21. model-00020-of-00316.safetensors +3 -0
  22. model-00021-of-00316.safetensors +3 -0
  23. model-00022-of-00316.safetensors +3 -0
  24. model-00023-of-00316.safetensors +3 -0
  25. model-00024-of-00316.safetensors +3 -0
  26. model-00025-of-00316.safetensors +3 -0
  27. model-00026-of-00316.safetensors +3 -0
  28. model-00027-of-00316.safetensors +3 -0
  29. model-00028-of-00316.safetensors +3 -0
  30. model-00029-of-00316.safetensors +3 -0
  31. model-00030-of-00316.safetensors +3 -0
  32. model-00031-of-00316.safetensors +3 -0
  33. model-00032-of-00316.safetensors +3 -0
  34. model-00033-of-00316.safetensors +3 -0
  35. model-00034-of-00316.safetensors +3 -0
  36. model-00035-of-00316.safetensors +3 -0
  37. model-00036-of-00316.safetensors +3 -0
  38. model-00037-of-00316.safetensors +3 -0
  39. model-00038-of-00316.safetensors +3 -0
  40. model-00039-of-00316.safetensors +3 -0
  41. model-00040-of-00316.safetensors +3 -0
  42. model-00041-of-00316.safetensors +3 -0
  43. model-00042-of-00316.safetensors +3 -0
  44. model-00043-of-00316.safetensors +3 -0
  45. model-00044-of-00316.safetensors +3 -0
  46. model-00045-of-00316.safetensors +3 -0
  47. model-00046-of-00316.safetensors +3 -0
  48. model-00047-of-00316.safetensors +3 -0
  49. model-00048-of-00316.safetensors +3 -0
  50. model-00049-of-00316.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DotsVLMForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "aux_loss_alpha": 0.001,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 1,
10
+ "ep_size": 1,
11
+ "first_k_dense_replace": 3,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 7168,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 18432,
16
+ "kv_lora_rank": 512,
17
+ "max_position_embeddings": 163840,
18
+ "model_type": "dots_vlm",
19
+ "moe_intermediate_size": 2048,
20
+ "moe_layer_freq": 1,
21
+ "n_group": 8,
22
+ "n_routed_experts": 256,
23
+ "n_shared_experts": 1,
24
+ "norm_topk_prob": true,
25
+ "num_attention_heads": 128,
26
+ "num_experts_per_tok": 8,
27
+ "num_hidden_layers": 61,
28
+ "num_key_value_heads": 128,
29
+ "num_nextn_predict_layers": 1,
30
+ "pretraining_tp": 1,
31
+ "q_lora_rank": 1536,
32
+ "qk_nope_head_dim": 128,
33
+ "qk_rope_head_dim": 64,
34
+ "rms_norm_eps": 1e-06,
35
+ "rope_scaling": {
36
+ "beta_fast": 32,
37
+ "beta_slow": 1,
38
+ "factor": 40,
39
+ "mscale": 1.0,
40
+ "mscale_all_dim": 1.0,
41
+ "original_max_position_embeddings": 4096,
42
+ "type": "yarn"
43
+ },
44
+ "rope_theta": 10000,
45
+ "routed_scaling_factor": 2.5,
46
+ "scoring_func": "sigmoid",
47
+ "seq_aux": true,
48
+ "tie_word_embeddings": false,
49
+ "quantization_config": {
50
+ "activation_scheme": "dynamic",
51
+ "fmt": "e4m3",
52
+ "quant_method": "fp8",
53
+ "weight_block_size": [
54
+ 128,
55
+ 128
56
+ ],
57
+ "modules_to_not_convert": [
58
+ "vision_tower",
59
+ "visual_tokenizer",
60
+ "vision_model",
61
+ "vision_proj"
62
+ ]
63
+ },
64
+ "topk_group": 4,
65
+ "topk_method": "noaux_tc",
66
+ "torch_dtype": "bfloat16",
67
+ "transformers_version": "4.33.1",
68
+ "use_cache": true,
69
+ "v_head_dim": 128,
70
+ "vocab_size": 129280,
71
+ "image_token_id": 128815,
72
+ "video_token_id": 128836,
73
+ "vision_config": {
74
+ "embed_dim": 1536,
75
+ "hidden_size": 7168,
76
+ "intermediate_size": 4224,
77
+ "num_hidden_layers": 42,
78
+ "num_attention_heads": 12,
79
+ "num_channels": 3,
80
+ "patch_size": 14,
81
+ "post_norm": true,
82
+ "rms_norm_eps": 1e-05,
83
+ "spatial_merge_size": 2,
84
+ "temporal_patch_size": 1,
85
+ "use_bias": false,
86
+ "attn_implementation": "flash_attention_2",
87
+ "init_merger_std": 0.02,
88
+ "initializer_range": 0.02,
89
+ "is_causal": false
90
+ }
91
+ }
model-00001-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140eef4b4970af58dae991445ecf5578b662876cab93a5319b76caa782a4efba
3
+ size 3971036960
model-00002-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ddfe1e57d628d815a125e0ab4e9ff2d09966a15889d6f2c422d398d67ebb916
3
+ size 2136430808
model-00003-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c4020aa103b103d5e6ad985d33560efad5ed63ac59dc22db3973b4c2e0da0bd
3
+ size 2143849304
model-00004-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50cab86ba9bc84929223d5143b8bb3cb26db5b79245248b3d8d18b73814eff33
3
+ size 2143849280
model-00005-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5864eecc067baf7ed6c4e02bb011f28942bcae450dd7e491cd8ca96c9b25b9e
3
+ size 2143849304
model-00006-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fda77cf1cbd6a641c30b307a5bd749662cdb46e1ed616809ec43f96e1161abc
3
+ size 2143849016
model-00007-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:167efe22be1f9007e3bac3b044f3f89eb32864a356577bfa207290c21c340406
3
+ size 2143815152
model-00008-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc52db8b811dbb31e4a03f6004ca8fcb085f9e470c943b2f1fddf13b17b5aa65
3
+ size 2143849296
model-00009-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28624fbf838282860f6764aa3443b31b93a6c40f85b475504b1bf078bb189aac
3
+ size 2143849304
model-00010-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5beecf49b060480749ba36af198c6b9ada276c8e03a47bbf65672af8c21cf73b
3
+ size 2143849288
model-00011-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b15e7d3c02179e8a3743cc2bfd4314225b3f3df9d825f01555531fb007ec1e
3
+ size 2143849120
model-00012-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700ecb615c000717230ce9c01164582e1c2e4af0944a33a90b9e409159ed6977
3
+ size 2143849008
model-00013-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821c568574b76b2dfce654518ff3660b213c0ec463482325e74e5ef6f3a1b509
3
+ size 2143815368
model-00014-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a255dc3486b210e592ba3313f47440291694ab19c3fa224895904f94fc3eb96b
3
+ size 2143849304
model-00015-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3c15cdd782be9c8bb9bcba38654d2e04b464afd44f4eb09c68d6d1bf820227
3
+ size 2143849280
model-00016-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b25f2e7e4f3374355f0e60ee1a9c26622ef92223a139832f3b5b30b70756e088
3
+ size 2143849232
model-00017-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b8b6d3d6901aa5111ebfd24fa5e694a99e7543dd363c527092bdf48fe2d6540
3
+ size 2143849000
model-00018-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6cf5eab1aeadecb4cc220c6229d8a7839b422d843118509778dc32f54711d99
3
+ size 2143815240
model-00019-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ac0f3402d544c2f7f3272e61ffb55d29c4fcae4b61a3dd9ce4460c2a4532b7
3
+ size 2143849296
model-00020-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ed7e83b29cb2c9a267054549f8c8d0b7cf3dd761fc71d330b96ccd101e737f
3
+ size 2143849288
model-00021-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de8d31ddce284d27a864659945fb676acff4b1c2261bc8c1963d9514ab05e375
3
+ size 2143849304
model-00022-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5058c76924d813d583a8c4b3392e6bf99dfce8e1953c9495364374b9e852ff0e
3
+ size 2143849048
model-00023-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6508ddc664302c7712fd150aca41de3cb49a78ffb621f5d1646473f491570e
3
+ size 2143815120
model-00024-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc0bfca7cd387667a473f721a0b7e33f9fe833fe1afc7a21a53eab689162e2c
3
+ size 2143849304
model-00025-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9dc6fbbe8274488016b8215b754959b21836e937d8ceb5530ab22f3246d9b6e
3
+ size 2143849296
model-00026-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04adaa7ec19fb3249ce6519cd855b809d8d2723db09903c65440e29fede30757
3
+ size 2143849296
model-00027-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c17faa3eb84ae55d93c65c79cce20fb6c865e243538d929f8de579a4fa76f5
3
+ size 2143849152
model-00028-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80eb6e02ee532f8a9462347b1daa5da9da68f380429f7777cd44eae283150161
3
+ size 2143849000
model-00029-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36da716c7c8571fdf84a2bb1f834edc87a40bf2b7b0c4a66bb637f8fa648db85
3
+ size 2143815320
model-00030-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fd227d8aaa1dfa2e5fa35ff528e2bee4c4a78176898e80952d40d5f5b5b46e5
3
+ size 2143849296
model-00031-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3580fd6c2ae6ac4e6d687e92648fb86b697046db27de1a817fae224e3f044f0
3
+ size 2143849296
model-00032-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af806e7eb07d58f970c681c274f6489c55d02ce88929c78a279bacc5736afa02
3
+ size 2143849256
model-00033-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48871fbbe9dbb6122c4b1e3bcb5bf426ebbdcb232e61b42733119f98cf44556e
3
+ size 2143849008
model-00034-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:632433b25649bba8351b916c4769270beabbf16365c7e3720fe1d5b323a93370
3
+ size 2143815200
model-00035-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db6611e0437eae1b89dc9900dc70d4460c32ed9e26aa01f02654c343010a09e1
3
+ size 2143849304
model-00036-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10f7c270eca4ac3f35c27fee20a21b5219ff0816290818cc4ee6a128b501d337
3
+ size 2143849288
model-00037-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ef71399823fc1d0c0a34f290363a34a373b228c53ece6407539a0334dc28fc
3
+ size 2143849304
model-00038-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddfc224df4880933157931480d7085ce252acc56e75a52c6561bf019fe35b92b
3
+ size 2143849080
model-00039-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58768b83de80168411cbfa9847d29582cc88e9d18a1d854efa44e59417f7e120
3
+ size 2135410280
model-00040-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23276ecceafd9ed7c1d3a474cd5a085c1e23f5296b0ccf7b452caf235eddd2fb
3
+ size 2137570216
model-00041-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c173eb5a93c722ce8b1b0b0b34d5b99e0c8c5c76d091102262f3f60c1f694df
3
+ size 2143849304
model-00042-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77df8344f0ab846fdf67845b6a8d703a117c78e0c47584dfe372096a46c97a8c
3
+ size 2143849288
model-00043-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b480d9cd1baceca0bea67d32d701c002494be5bed6509ccc283f4e74cdbae4
3
+ size 2143849184
model-00044-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca457faefcfb84a05e1ea88bcbe56c2f94591669f63cbf3cc7750a516db94ad
3
+ size 2143849008
model-00045-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:541db3884c0b4bddce9ce1a9838d4d8d53745fa0996b70e6fe0ea91cbe01c541
3
+ size 2143815288
model-00046-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:162b8a01f874ae2d54c92b15260ddf7d674f586a966c8d458556e236c529d8bb
3
+ size 2143849304
model-00047-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d1c775bf08b35904effa50f003cefe169ed90a52f2ac09ab03ca6bc2c6e315b
3
+ size 2143849280
model-00048-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad37e81259fd194e6e9dfd3a1e001be387eadc0d076a11d404411d06a7530ff5
3
+ size 2143849304
model-00049-of-00316.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1969245636441726816cccb2c5585beaf139cccc40021a5394a159565e16ee7a
3
+ size 2143849000