OwenArli commited on
Commit
036d608
·
verified ·
1 Parent(s): 441c9d4

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. .gitattributes +1 -0
  2. config.json +80 -0
  3. generation_config.json +10 -0
  4. model-00001-of-00073.safetensors +3 -0
  5. model-00002-of-00073.safetensors +3 -0
  6. model-00003-of-00073.safetensors +3 -0
  7. model-00004-of-00073.safetensors +3 -0
  8. model-00005-of-00073.safetensors +3 -0
  9. model-00006-of-00073.safetensors +3 -0
  10. model-00007-of-00073.safetensors +3 -0
  11. model-00008-of-00073.safetensors +3 -0
  12. model-00009-of-00073.safetensors +3 -0
  13. model-00010-of-00073.safetensors +3 -0
  14. model-00011-of-00073.safetensors +3 -0
  15. model-00012-of-00073.safetensors +3 -0
  16. model-00013-of-00073.safetensors +3 -0
  17. model-00014-of-00073.safetensors +3 -0
  18. model-00015-of-00073.safetensors +3 -0
  19. model-00016-of-00073.safetensors +3 -0
  20. model-00017-of-00073.safetensors +3 -0
  21. model-00018-of-00073.safetensors +3 -0
  22. model-00019-of-00073.safetensors +3 -0
  23. model-00020-of-00073.safetensors +3 -0
  24. model-00021-of-00073.safetensors +3 -0
  25. model-00022-of-00073.safetensors +3 -0
  26. model-00023-of-00073.safetensors +3 -0
  27. model-00024-of-00073.safetensors +3 -0
  28. model-00025-of-00073.safetensors +3 -0
  29. model-00026-of-00073.safetensors +3 -0
  30. model-00027-of-00073.safetensors +3 -0
  31. model-00028-of-00073.safetensors +3 -0
  32. model-00029-of-00073.safetensors +3 -0
  33. model-00030-of-00073.safetensors +3 -0
  34. model-00031-of-00073.safetensors +3 -0
  35. model-00032-of-00073.safetensors +3 -0
  36. model-00033-of-00073.safetensors +3 -0
  37. model-00034-of-00073.safetensors +3 -0
  38. model-00035-of-00073.safetensors +3 -0
  39. model-00036-of-00073.safetensors +3 -0
  40. model-00037-of-00073.safetensors +3 -0
  41. model-00038-of-00073.safetensors +3 -0
  42. model-00039-of-00073.safetensors +3 -0
  43. model-00040-of-00073.safetensors +3 -0
  44. model-00041-of-00073.safetensors +3 -0
  45. model-00042-of-00073.safetensors +3 -0
  46. model-00043-of-00073.safetensors +3 -0
  47. model-00044-of-00073.safetensors +3 -0
  48. model-00045-of-00073.safetensors +3 -0
  49. model-00046-of-00073.safetensors +3 -0
  50. model-00047-of-00073.safetensors +3 -0
.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
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GptOssForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 200002,
8
+ "experts_per_token": 4,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2880,
12
+ "initial_context_length": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2880,
15
+ "layer_types": [
16
+ "sliding_attention",
17
+ "full_attention",
18
+ "sliding_attention",
19
+ "full_attention",
20
+ "sliding_attention",
21
+ "full_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 131072,
54
+ "model_type": "gpt_oss",
55
+ "num_attention_heads": 64,
56
+ "num_experts_per_tok": 4,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "num_local_experts": 128,
60
+ "output_router_logits": false,
61
+ "pad_token_id": 199999,
62
+ "rms_norm_eps": 1e-05,
63
+ "rope_scaling": {
64
+ "beta_fast": 32.0,
65
+ "beta_slow": 1.0,
66
+ "factor": 32.0,
67
+ "original_max_position_embeddings": 4096,
68
+ "rope_type": "yarn",
69
+ "truncate": false
70
+ },
71
+ "rope_theta": 150000,
72
+ "router_aux_loss_coef": 0.9,
73
+ "sliding_window": 128,
74
+ "swiglu_limit": 7.0,
75
+ "tie_word_embeddings": false,
76
+ "torch_dtype": "bfloat16",
77
+ "transformers_version": "4.56.0.dev0",
78
+ "use_cache": true,
79
+ "vocab_size": 201088
80
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 199998,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 200002,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.56.0.dev0"
10
+ }
model-00001-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51b5b69e7feecbc961896afbe7be9a02fce772d236eb5d14d98bf9f93565e872
3
+ size 1212106064
model-00002-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f8d893fc4fbd27a07d2454114d5cc84821fa18d7575b625aa184b31ef0a572
3
+ size 4248207640
model-00003-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26fb7705dba6ce529158ecea8863e20dc2c197790c159f3ec15b865b8474c97a
3
+ size 2177954736
model-00004-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda6a71a050e68fe98ddfc12c0e3e86234b29d2ee5a6ba9083cabcc9e173563f
3
+ size 4248207640
model-00005-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a37774982420254a3c7141b981aa37878713d6bc6f78a756295cd9e41c1ab88
3
+ size 2177954736
model-00006-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b81738668bce7b58ec8cef5e8c25b1e2b7afafcd1af7913da2788838263bd0
3
+ size 4248207640
model-00007-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c25b0c1f0d5f64594529628151ace3ae838869c744c361cd5421165442e26e
3
+ size 2177954736
model-00008-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b43d83c403e92882c79cdfbeb8b80e30d0d7fe58329ab8d3a8a13db0c1d7c5d
3
+ size 4248207640
model-00009-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fc61132427d0002e559feca0a040ddcc2be59557bc9b713c5011702c25e5b6
3
+ size 2177954736
model-00010-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc516fd1e058767eb5d566b81f2619fc9319aed76409628d94b9fda5e4994a0
3
+ size 4248207640
model-00011-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153eef134702ea1df876220d0e3873e47b124b7764dabc8c64f25a8247761fec
3
+ size 2177954736
model-00012-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39b2a45ac61f5b5d44e5a2df4b88643f8c7d57545b06c60121d954a9598599c1
3
+ size 4248207640
model-00013-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11ceba841dfdd14f0e2b313e676c48c4d66b5824a2fdfa25aa327fabccb227f2
3
+ size 2177954736
model-00014-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a4ba78d4b340e08bcdb3fbfb48c26cc57abd581046b6a2a6620b9c63cca14aa
3
+ size 4248207640
model-00015-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c5e76d8bd303eba203bb00f9ab3dcb4cffa22efe3c400c63c4eb146dd1d744
3
+ size 2177954736
model-00016-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:925cd470b083f8ce05484d991c989419873eecf562080947d4c64649ab56677d
3
+ size 4248207640
model-00017-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0ccd83bcd726ee1d758e4eda1d181fc9725e19dfd7ed6326e60b2403f394010
3
+ size 2177954736
model-00018-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52b5fe061cefc784b2fb5a09ce6f30fe1fa6641103a141a5b8722df2a48aff8
3
+ size 4248207640
model-00019-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:491cc447b9ac3010ddd8a5a1a2debfbf089a5fd1bececa2bca9589e23280b512
3
+ size 2177954736
model-00020-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3484899ce81bacff6cf71f3e225152d61b3f688906bdaca527c87c5eb35d7c1f
3
+ size 4248207640
model-00021-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd51c755fc6bf56bbe9eff6fe4045ec3b6e36880b88a385304ce9b8e8e1d348f
3
+ size 2177954688
model-00022-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d18647e59b8982622412fa33d9c8defbac9441670fedeb94bf216382f904e48
3
+ size 4248207640
model-00023-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be9778c9a50388d090112715fd496790d576e6f481c4fdedfa5fae583d8b33d8
3
+ size 2177954720
model-00024-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f75eeb2761915a28fd12ae35d2fa13b6b984d9c6829184dc6a81bb778d1811c2
3
+ size 4248207640
model-00025-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c847991ac276820b51f8b23afb509b3c582ab9a6bbc0d737ee6148aa58215cf7
3
+ size 2177954720
model-00026-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d69f06e29de3eeb3e8df6353d418cfca5a6abb432f90b95c750252e5d3b7e1
3
+ size 4248207640
model-00027-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a4bfc54df034fbc9efe97ad0c08daedf84287c6f360c88d21a762345baff2ad
3
+ size 2177954720
model-00028-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2301da5402b74812725f99d892af657a421d7d3ff1fedf3309c28aa0fa0e4353
3
+ size 4248207640
model-00029-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1760d57e597bea02cb84767a4f05aa4eb455a3e62bf3a0d5c4057573c5a9f1c6
3
+ size 2177954720
model-00030-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8c1f5337c4b372da5d49cfeca7996e85cf3f8af0323359abfc5a38539db4d1
3
+ size 4248207640
model-00031-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee9db976e1804aa135d517a53275a72c450cd6b33b57cedc2bf1a8cedb2d2eb4
3
+ size 2177954720
model-00032-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9dc8df6da9507d6f99547ed7b6ab17793cbcd5a81c0c2f3439ff8f6c1d10c9
3
+ size 4248207640
model-00033-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f148d7a6120c88c1087a9fe945371f1d1430bd272e21fcdebf358de56cb62e
3
+ size 2177954720
model-00034-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2278f08494e6ef08a3e4b5794fc650970b01bb6652502c3bf861d9ee39024d52
3
+ size 4248207640
model-00035-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad88fc9f3d9c216003a63a4a43503f662aa6f7ceec98f53d9f899ecf78420e0
3
+ size 2177954720
model-00036-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d28428c507c8b4e042c656f2db6c30fc9db7dd6f6c0157dcda930c2a3ea4d11c
3
+ size 4248207640
model-00037-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5f7c63cacd4a0f5ddef7b5a382652504839d6fde62e53fad13bd7c9cec8c50
3
+ size 2177954720
model-00038-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9704e3b5209e51b7310530e1da1e31b4aafb290a21b1957990b59ee98c08312f
3
+ size 4248207640
model-00039-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c2a8cbe5c277b58d43031b4f4b8f120a431a305109f3f3b277c3147d3888462
3
+ size 2177954720
model-00040-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63132593ac1bd4883db66340d38ef61685065e53db5ac40276bbfc1d83fb8bb8
3
+ size 4248207640
model-00041-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c457d4cf3c9f013009a45e4795cd50f015cc2d405a7e0b9ec168dcbf8f22265
3
+ size 2177954720
model-00042-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39c7084ce12ee967b6dd15c8e1849fa550d50fd8e7d123064c3b3b5a233118a
3
+ size 4248207640
model-00043-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5773134ef28cfc7cf7f4af256242b14e543947d9fff2bf4a095406a73863c5f
3
+ size 2177954720
model-00044-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a3cfc8f6772d9ec8ccbbd1213069d0b8213d1f7bf4658011ac9fcb12504e941
3
+ size 4248207640
model-00045-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8964545596d0aa661b9c9a91abfdda250bd17f6310670f130e0d08f6f64ea3b3
3
+ size 2177954752
model-00046-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1939048181675b836a1f11862169988e54ecf788d4b74421f664052d565c07a
3
+ size 4248207640
model-00047-of-00073.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38a17484c45aed703077f81d42f438491d080999fc12e45a3edd9bbf5f5230a9
3
+ size 2177954752