Hugging Face's logo

allenai
/
Llama-3.1-Tulu-3-405B

Text Generation
Transformers
PyTorch
Safetensors
English
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
1
natolambert commited on
Commit
f90a39a
·
verified ·
1 Parent(s): b89fac2

Add files using upload-large-folder tool

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 +4 -3
  2. generation_config.json +1 -1
  3. model-00001-of-00191.safetensors +3 -0
  4. model-00002-of-00191.safetensors +3 -0
  5. model-00004-of-00191.safetensors +3 -0
  6. model-00005-of-00191.safetensors +3 -0
  7. model-00007-of-00191.safetensors +3 -0
  8. model-00008-of-00191.safetensors +3 -0
  9. model-00009-of-00191.safetensors +3 -0
  10. model-00013-of-00191.safetensors +3 -0
  11. model-00014-of-00191.safetensors +3 -0
  12. model-00015-of-00191.safetensors +3 -0
  13. model-00016-of-00191.safetensors +3 -0
  14. model-00017-of-00191.safetensors +3 -0
  15. model-00019-of-00191.safetensors +3 -0
  16. model-00020-of-00191.safetensors +3 -0
  17. model-00021-of-00191.safetensors +3 -0
  18. model-00022-of-00191.safetensors +3 -0
  19. model-00023-of-00191.safetensors +3 -0
  20. model-00024-of-00191.safetensors +3 -0
  21. model-00025-of-00191.safetensors +3 -0
  22. model-00026-of-00191.safetensors +3 -0
  23. model-00027-of-00191.safetensors +3 -0
  24. model-00028-of-00191.safetensors +3 -0
  25. model-00029-of-00191.safetensors +3 -0
  26. model-00030-of-00191.safetensors +3 -0
  27. model-00031-of-00191.safetensors +3 -0
  28. model-00032-of-00191.safetensors +3 -0
  29. model-00033-of-00191.safetensors +3 -0
  30. model-00034-of-00191.safetensors +3 -0
  31. model-00035-of-00191.safetensors +3 -0
  32. model-00036-of-00191.safetensors +3 -0
  33. model-00037-of-00191.safetensors +3 -0
  34. model-00039-of-00191.safetensors +3 -0
  35. model-00040-of-00191.safetensors +3 -0
  36. model-00041-of-00191.safetensors +3 -0
  37. model-00042-of-00191.safetensors +3 -0
  38. model-00043-of-00191.safetensors +3 -0
  39. model-00044-of-00191.safetensors +3 -0
  40. model-00045-of-00191.safetensors +3 -0
  41. model-00046-of-00191.safetensors +3 -0
  42. model-00047-of-00191.safetensors +3 -0
  43. model-00048-of-00191.safetensors +3 -0
  44. model-00049-of-00191.safetensors +3 -0
  45. model-00051-of-00191.safetensors +3 -0
  46. model-00052-of-00191.safetensors +3 -0
  47. model-00056-of-00191.safetensors +3 -0
  48. model-00057-of-00191.safetensors +3 -0
  49. model-00059-of-00191.safetensors +3 -0
  50. model-00060-of-00191.safetensors +3 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/oe-adapt-default/costah/models/405B_finetune_successful",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -7,6 +7,7 @@
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
  "eos_token_id": 128001,
 
10
  "hidden_act": "silu",
11
  "hidden_size": 16384,
12
  "initializer_range": 0.02,
@@ -29,7 +30,7 @@
29
  "rope_theta": 500000.0,
30
  "tie_word_embeddings": false,
31
  "torch_dtype": "bfloat16",
32
- "transformers_version": "4.43.4",
33
- "use_cache": true,
34
  "vocab_size": 128264
35
  }
 
1
  {
2
+ "_name_or_path": "/weka/oe-adapt-default/hamishi/405b_dpo_v4",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
  "eos_token_id": 128001,
10
+ "head_dim": 128,
11
  "hidden_act": "silu",
12
  "hidden_size": 16384,
13
  "initializer_range": 0.02,
 
30
  "rope_theta": 500000.0,
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.47.1",
34
+ "use_cache": false,
35
  "vocab_size": 128264
36
  }
generation_config.json CHANGED
@@ -5,5 +5,5 @@
5
  "eos_token_id": 128001,
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
- "transformers_version": "4.43.4"
9
  }
 
5
  "eos_token_id": 128001,
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.47.1"
9
  }
model-00001-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a5c2153dbd137f4878a65a5cfba55dafea83c2266f2388e379232829cd79c7
3
+ size 4806935024
model-00002-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e77fe052a1111505a8d5ad3e99505c3a34e11d7bbf85f04a36d0f300680a6ba
3
+ size 4026532224
model-00004-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551cf09848addf0279b0350e6c256ce0d9f0516e76b539a00696fa9489ed189b
3
+ size 4630578112
model-00005-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e0aefd62653de5a9d37cada40854ff0fff12ba76662b8f11dd451e89cb40d2
3
+ size 3489661192
model-00007-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a39747cb7c2b0ff96140bd2aa5072f82bb2c79c416cbb096354fecb3ad0885b0
3
+ size 4630578112
model-00008-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15b5972f19515effc0ab0f060e7fc05b901e41b9a921f589cf29e6d82d8e93d
3
+ size 3489661192
model-00009-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6412ffe08058fbb7963d2bc3c6ebcc9fe07b2f0935eefbab889d33ae870a2358
3
+ size 4630578112
model-00013-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:602fb71a96e108b1f28f7d0b67162ea438ebb0dce7365d1d1434df998f5f9986
3
+ size 4630578112
model-00014-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a838b9f4f9f5724c91d163e574d5190c6fe7eb44568eca842e510c4e64f366a
3
+ size 3489661192
model-00015-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc3a6eb6c3b87bb40c6883e58c6de9f2e67b824d1e31758ac63b7e87a979b4c
3
+ size 4630578112
model-00016-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e50e4d6fb73453e4fdce4a2a1bc1c8f7bb44b2a6283fa744c7f734e5fce51a22
3
+ size 4630578120
model-00017-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234127f7830d59bace8a4e2e8fc5f276486df68397ffae178e8da65f8691f82e
3
+ size 3489661192
model-00019-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71682cca2e0d7659475e5631af48ee48b4f472aa06c4128b1eb81f4ac09ba818
3
+ size 4630578120
model-00020-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd4d7017571ec2c14b945cff22733775876ce053e354fb579b63f2d91db1af66
3
+ size 3489661192
model-00021-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e958b43e6e61ec6ae8eec43103484dbcbfe5c57f93c0548af4e59abaa5b1bef
3
+ size 4630578120
model-00022-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37af015863a1aee00b9cf1ef804c262a1c7fff03f55ea078dccbf2f908fc9346
3
+ size 4630578120
model-00023-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8202ee4b7845428c1ed59346a0f31bf101067e948ebba924849ccd436568780b
3
+ size 3489661192
model-00024-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3181372256f027bde4350f284af42887e4f43047c8bbcd154b42cc00f75eafde
3
+ size 4630578120
model-00025-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157429100e321ff9a70d1a381ce42f927a3db79a60ba5a6693b134160259886f
3
+ size 4630578120
model-00026-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:293a211527d4a303e5136b86ea1d52d70eedd1ffd4c4dccb9381dfc6bb99871c
3
+ size 3489661192
model-00027-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef9a65b772c83ba0209c9ba5821277c6b7347e91466404a6e43020b12fabbf54
3
+ size 4630578120
model-00028-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c1b86db7492bc5dd14379575acfbb7eea24feaa566a27a32dd1f1c7dbdc248a
3
+ size 4630578120
model-00029-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75933d94dbacc026a2d54f00c5f4cfabf9c2388f77f96c270389a8b9b8df6d78
3
+ size 3489661192
model-00030-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c854123f6bb1355108e0bc3510375db0518c9fafd847c5603e42c6f22298bafc
3
+ size 4630578120
model-00031-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab8acbcaf9ec8a9fa99bb6e50c69f675f7cac5d0af4995a937ed8dbab4dd183
3
+ size 4630578120
model-00032-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa4a8cf325dce210c8ea523d819781a776a139c4ce4d9489c6ac90851ddad569
3
+ size 3489661192
model-00033-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1bea53f2db158f69ccc2997f6101dc7a9d458b91b76c13c50b5765c74943153
3
+ size 4630578120
model-00034-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36eb0b10d9e0a5bb36fbe8a1681687d905c2165e4a81cd2fb14dfbf3ead9dcac
3
+ size 4630578120
model-00035-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aee0c42c487492f696dc3c9fe0ec87b508b0b680d19c6e2dfe9a2560b756e22
3
+ size 3489661192
model-00036-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a659b66fe9da3c807b588975231113e6a33dee5c6edd205bfa17c2d654606f5
3
+ size 4630578120
model-00037-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef26b2c0614ad0d6a615209dce12980a18380c4924d4b429998a12d540438cc
3
+ size 4630578120
model-00039-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6587762b654e498ef6f7c0cfe0d0bf32212aad017eba94923343e7c13feeaeb4
3
+ size 4630578120
model-00040-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b5fc8f2372d80be0315c4aebb0436d06f2255ec196f5e83b8ffe57b5ad58da8
3
+ size 4630578120
model-00041-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03330ddba4a9591e33317c4c21c0766d4f3be3f118f9c48a2398a2206cfc6213
3
+ size 3489661192
model-00042-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d9d796998425f539c3cc798fd3634e3d86ed34c80c8f1c9a38a3b34dfc630d
3
+ size 4630578120
model-00043-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61359b81019551b81d8d57f95e4a8b949dedc8749d10105cce3aa0df6e49bc4
3
+ size 4630578120
model-00044-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e91720521b2ad86c3c8915dd568b6dbed3a7db99d7993ee84205e0fa8b08729
3
+ size 3489661192
model-00045-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69c6ee8e5887a8ce02494e2406d890b3b12a1f00af64adba87988384df2f6400
3
+ size 4630578120
model-00046-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7fa5875c1c281648845f7e8861e411cd739603140f8da68f53a5c0c43fb84c
3
+ size 4630578120
model-00047-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65b4646e145739d9045768b1a050370b663e6165562fb7be46945377397894c
3
+ size 3489661192
model-00048-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21d41b14c082bf2b55c1ce700c1618a6dad38f2ae0224dce19e1d288c137157f
3
+ size 4630578120
model-00049-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e31f48bcc72c250c6d9977bcc2afba7e8e424551eeaac73211efb54394ad83b
3
+ size 4630578120
model-00051-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11a6918aeec20eee76d5646981efb4cf31f03720209a3dcd68f51d55999517a
3
+ size 4630578120
model-00052-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23e7a860438f1b6bb927a4eba058df02e910122d00ecc80f14d3f4c61686f30e
3
+ size 4630578120
model-00056-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe483c26806379909d2ffce560a79a60782d890f410c129c94f888ab34fc575
3
+ size 3489661192
model-00057-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b10866f5f11b03cb5c3c98e776c25c8ceb6596b77c24cdcc207fff88cb66c535
3
+ size 4630578120
model-00059-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e06a9952279a0a12e7c955b4b8320b7e16f6567db4a14aa9feb786ff2b9882
3
+ size 3489661192
model-00060-of-00191.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47094a83933750a0fe7ac6d9041a74255ac5934255ae1303800bb9b312d0d49
3
+ size 4630578120