Hugging Face's logo

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

Text Generation
Transformers
PyTorch
English
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
natolambert commited on
Commit
7c21854
·
verified ·
1 Parent(s): dc21a0d

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. .gitattributes +1 -0
  2. config.json +36 -0
  3. generation_config.json +9 -0
  4. metadata.json +1 -0
  5. pytorch_model-00001-of-00191.bin +3 -0
  6. pytorch_model-00002-of-00191.bin +3 -0
  7. pytorch_model-00004-of-00191.bin +3 -0
  8. pytorch_model-00005-of-00191.bin +3 -0
  9. pytorch_model-00006-of-00191.bin +3 -0
  10. pytorch_model-00007-of-00191.bin +3 -0
  11. pytorch_model-00009-of-00191.bin +3 -0
  12. pytorch_model-00010-of-00191.bin +3 -0
  13. pytorch_model-00011-of-00191.bin +3 -0
  14. pytorch_model-00012-of-00191.bin +3 -0
  15. pytorch_model-00013-of-00191.bin +3 -0
  16. pytorch_model-00014-of-00191.bin +3 -0
  17. pytorch_model-00015-of-00191.bin +3 -0
  18. pytorch_model-00019-of-00191.bin +3 -0
  19. pytorch_model-00020-of-00191.bin +3 -0
  20. pytorch_model-00022-of-00191.bin +3 -0
  21. pytorch_model-00023-of-00191.bin +3 -0
  22. pytorch_model-00024-of-00191.bin +3 -0
  23. pytorch_model-00025-of-00191.bin +3 -0
  24. pytorch_model-00026-of-00191.bin +3 -0
  25. pytorch_model-00027-of-00191.bin +3 -0
  26. pytorch_model-00028-of-00191.bin +3 -0
  27. pytorch_model-00029-of-00191.bin +3 -0
  28. pytorch_model-00030-of-00191.bin +3 -0
  29. pytorch_model-00031-of-00191.bin +3 -0
  30. pytorch_model-00032-of-00191.bin +3 -0
  31. pytorch_model-00034-of-00191.bin +3 -0
  32. pytorch_model-00035-of-00191.bin +3 -0
  33. pytorch_model-00036-of-00191.bin +3 -0
  34. pytorch_model-00037-of-00191.bin +3 -0
  35. pytorch_model-00038-of-00191.bin +3 -0
  36. pytorch_model-00039-of-00191.bin +3 -0
  37. pytorch_model-00040-of-00191.bin +3 -0
  38. pytorch_model-00041-of-00191.bin +3 -0
  39. pytorch_model-00044-of-00191.bin +3 -0
  40. pytorch_model-00046-of-00191.bin +3 -0
  41. pytorch_model-00047-of-00191.bin +3 -0
  42. pytorch_model-00048-of-00191.bin +3 -0
  43. pytorch_model-00049-of-00191.bin +3 -0
  44. pytorch_model-00050-of-00191.bin +3 -0
  45. pytorch_model-00051-of-00191.bin +3 -0
  46. pytorch_model-00054-of-00191.bin +3 -0
  47. pytorch_model-00055-of-00191.bin +3 -0
  48. pytorch_model-00056-of-00191.bin +3 -0
  49. pytorch_model-00057-of-00191.bin +3 -0
  50. pytorch_model-00058-of-00191.bin +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 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/oe-adapt-default/costah/models/405B_finetune_successful",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
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,
14
+ "intermediate_size": 53248,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 128,
19
+ "num_hidden_layers": 126,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.47.1",
34
+ "use_cache": true,
35
+ "vocab_size": 128264
36
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.47.1"
9
+ }
metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_name": "dpo_tune_cache", "model_type": "dpo", "datasets": ["ai2-adapt-dev/405b_preference_mix"], "base_model": "/oe-adapt-default/costah/models/405B_finetune_successful", "wandb_path": "https://wandb.ai/ai2-llm/open_instruct_internal/runs/v1rhfn1m", "beaker_experiment": "https://beaker.org/ex/01JJ4QRZ31SH79AHVM6WWDVJB4/", "beaker_datasets": ["https://beaker.org/ds/01JJ4QRZ4X8RKSGP939745BWPP", "https://beaker.org/ds/01JJ4QRZA364S625K42YEJC471", "https://beaker.org/ds/01JJ4QRZF5AKF5JXS7G79CTWXH", "https://beaker.org/ds/01JJ4QRZMBXP67FBN3MKYB90M8", "https://beaker.org/ds/01JJ4QRZT9PHZ1TD216TKNZ0C0", "https://beaker.org/ds/01JJ4QS000A3V672TFZHRBCSFE", "https://beaker.org/ds/01JJ4QS04TZM482VA9A9QV04H5", "https://beaker.org/ds/01JJ4QS09J57HA4XP2TAYJMBHY", "https://beaker.org/ds/01JJ4QS0F18PHA5Y44W1TCTK1N", "https://beaker.org/ds/01JJ4QS0KZK07C8JKQQ39JZADN", "https://beaker.org/ds/01JJ4QS0STGPH2151E331EWJR7", "https://beaker.org/ds/01JJ4QS0Z26WZD9131ZTDMCSM7", "https://beaker.org/ds/01JJ4QS157W1A3J9VD2WYX7DRN", "https://beaker.org/ds/01JJ4QS1BVQKR41YH4G5JC9NQ3", "https://beaker.org/ds/01JJ4QS1H1KM8XBQXWAR3RCTXA", "https://beaker.org/ds/01JJ4QS1Q0TS69T26BTETH3MTH", "https://beaker.org/ds/01JJ4QS1W1QEES6EQMK4RHA5S8", "https://beaker.org/ds/01JJ4QS213SH8VF4CYWKHKCGF0", "https://beaker.org/ds/01JJ4QS25TY2JCKAK423RHYCWX", "https://beaker.org/ds/01JJ4QS2AN2XMTDDTEMTYGNPAC", "https://beaker.org/ds/01JJ4QS2FMJTDNSPXW953KS7VB", "https://beaker.org/ds/01JJ4QS2N7K26FJZXJ9QE6A9X2", "https://beaker.org/ds/01JJ4QS2T9TW1ZZT1E5TWYZP4D", "https://beaker.org/ds/01JJ4QS2Z8HPSPAT47TCH4VK6A", "https://beaker.org/ds/01JJ4QS346VN1D1Y67GAAX5TC7", "https://beaker.org/ds/01JJ4QS391HH9PVZMZZC1GSGSY", "https://beaker.org/ds/01JJ4QS3E2NSTJ2XF2R5VQFF7M", "https://beaker.org/ds/01JJ4QS3K0V50J4FNVPQZRA74K", "https://beaker.org/ds/01JJ4QS3QTH2CQM8ERMKTFC8H2", "https://beaker.org/ds/01JJ4QS3WS89MVZRK50NE3WRM2", "https://beaker.org/ds/01JJ4QS41QJ2CSVZQJE0KHC75X", "https://beaker.org/ds/01JJ4QS46SGE41SRG0XYQ6TY63"]}
pytorch_model-00001-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf2e1c55a115e9bf0b130ead654afad71b768b775ba1a05378d2c0d3ab3a1618
3
+ size 4806936944
pytorch_model-00002-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41d00ad652a37a9bedc0d483688bf65f69e293df8842056ca53ab46978fc476d
3
+ size 4026533863
pytorch_model-00004-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0756f79c6675ed23fcf171c49489a14375139a758a3464b7d9f42877855eefa
3
+ size 4630580764
pytorch_model-00005-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4311d860602a353eb2ba3b8729cfea97a1ba353606a277a4a088942f6be6749
3
+ size 3489662678
pytorch_model-00006-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f8c7cd3715c92da69508e3fc7ef211ffb9320176c24154481afe75c1643c196
3
+ size 4630580764
pytorch_model-00007-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e4642c4594b880e48d1a5d4b933f487f549bb73b32522d4b91b71e2a4c52e3
3
+ size 4630580764
pytorch_model-00009-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2138106cb4a6c264e5017510adfa2960b684f9d6d023353bf75ac3e4a796db69
3
+ size 4630580764
pytorch_model-00010-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a64bb8fb16aa2c6a04776fa15fdccdd70c773a59e87882a1b361703b7275ba2
3
+ size 4630580764
pytorch_model-00011-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab5b34a0d4db6b0ee8b1ce33e57eefaa358e4fbe6f19394af76a8a3dcc23b7e7
3
+ size 3489662678
pytorch_model-00012-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe45e6274d71626231412097a292e50adbb587785dce0e6147f47f834367901
3
+ size 4630580764
pytorch_model-00013-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc3cafdf2601dfd2d7f153c06053f08fa0b130232d8c3b0d33e34d992e6c2e3
3
+ size 4630580764
pytorch_model-00014-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:726a80237b9b945e46a5d762b144500bc2a37bcb1a9c8a97b28b387aa8b7f63c
3
+ size 3489662678
pytorch_model-00015-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5eb54ddb4b3a5d64b8394d3adc94bc1cc63ca115cf3ff2cc9e0d421b3b2a4bf
3
+ size 4630580764
pytorch_model-00019-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea003813af99a76b754d215274f41bd6967b5c195000ccf321ef6438eb253c6
3
+ size 4630580764
pytorch_model-00020-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d261ca85e50871964f3b00925f9c8135a475c91157159dcbef6b4ae91570eb9
3
+ size 3489662678
pytorch_model-00022-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f68f15c2a98eb49e7b3d9e42473778b558347a4a509c3a1b752af2fd16de47
3
+ size 4630580764
pytorch_model-00023-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b669b9f7388bc28e9e3223d96901e69d586fd90bac6f7834c6cfb82c713a2acf
3
+ size 3489662678
pytorch_model-00024-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970949fe23424bc3af8c62e0d46439a0cb09fc1974f9f1ee0db355d7122d4d11
3
+ size 4630580764
pytorch_model-00025-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f9dde38b78e02a346d828c1bfadd6cc477536561a42ed8c674041de0bf0fce
3
+ size 4630580764
pytorch_model-00026-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf925bc9b7935acda05d4d8ec27cc42ffe6e2a24f9c21594ae31b7e0f5dca78
3
+ size 3489662678
pytorch_model-00027-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81223042ce073e05edf45f6deecab302fd2eab92f8b2d4ec07d3b6805ce7072
3
+ size 4630580764
pytorch_model-00028-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c93d6abaa734fdc04e1f1e863442d647191f538102c0990840678bd12766387
3
+ size 4630580764
pytorch_model-00029-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d715dd48b381d0c657be234d775309884d7145917202f1dd9ae2e2cf1fe59adb
3
+ size 3489662678
pytorch_model-00030-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a62e9f2f3c095d483ec7c9bd72d8005b3e8b7f0792aaf56e779eaedb6a8ce6
3
+ size 4630580764
pytorch_model-00031-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c04437c59a1e8ac05ed521d218048f2973aacacdf7beffb34b2b474c0bf6cc18
3
+ size 4630580764
pytorch_model-00032-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528606b66c020948a4c2a9c0ca9b1e8b1ac3f6f4da9ccc04b55f760a4ad5817e
3
+ size 3489662678
pytorch_model-00034-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:608be02773ec1d3d70f37743fe63c6ecea2bdd7b6854ee605e8db2805bbfa955
3
+ size 4630580764
pytorch_model-00035-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5692b5cf6b8cc8298637519e1424555ff2adfdedadd093f0bcc0b3241e1c1b1d
3
+ size 3489662678
pytorch_model-00036-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ddbd672d526b6af200fb8fbc05165e75cd05b8f2e205acc6d7851b08fd6f68d
3
+ size 4630580764
pytorch_model-00037-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f34357c32670c97c6eb57e36c3222d43d959346e53c0b1f147265ff40a2a62
3
+ size 4630580764
pytorch_model-00038-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a87c119ab700c934d26908869000a0d83dd786a02b92c7751c8ae4f943dcc841
3
+ size 3489662678
pytorch_model-00039-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3876548388777f52ea7dbf3a2e513f2f140e2f7cd1def3e2be612a24e9e4ffaf
3
+ size 4630580764
pytorch_model-00040-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b5b3c9569f7c7d285b25b44a8fff9e210f8018d3ed72db9de8d502923c6bd1
3
+ size 4630580764
pytorch_model-00041-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b778bace05ca621c3ac006b9c22953546078181524708efd1097c733d55cbca6
3
+ size 3489662678
pytorch_model-00044-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5365eb67d76a5f907a26556de48f3cdfb9aa2158ab0b265582ead7535e823ab
3
+ size 3489662678
pytorch_model-00046-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:760b07e00973ccf38e9b384eb8835dc93f2f68c2713a0fb3dc479e548d47c4bb
3
+ size 4630580764
pytorch_model-00047-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96610c0c7c300ca77e2dbfb20366ca363aa0b7b015be5e118d191420d7527758
3
+ size 3489662678
pytorch_model-00048-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b391de2d50d08c9f39fad63fd7568c47898a83420a90856ebde6a92a0cedfe5
3
+ size 4630580764
pytorch_model-00049-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75163f3075a0fc1a3b35e4b936d8b1228a0137d0bc389eb862567fd7701584a4
3
+ size 4630580764
pytorch_model-00050-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d1267940808131c25f245150994ad530ab62415d0a6d6c2d518700073b793b5
3
+ size 3489662678
pytorch_model-00051-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d234755c451728060a4bd4ee790646826e5702ac9bed38fe6530e419f0133121
3
+ size 4630580764
pytorch_model-00054-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c298c52d93a8fe4006fc02e9a1d670f74163c3a9c968d71c8c6db7005a02faf
3
+ size 4630580764
pytorch_model-00055-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd2a3695cac6af9b5deef7793e45e0f6492264a1b8a7cc16e3426bd50582dab
3
+ size 4630580764
pytorch_model-00056-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dc841bb02a948c5a857a5782cabe00b70fe4b4ab79d008ba1e34fb698dce7be
3
+ size 3489662678
pytorch_model-00057-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f91db550d033a9bfed60e7c8a0b46722b943acc579d408599498210b562f82e0
3
+ size 4630580764
pytorch_model-00058-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b82f39bc4cfce7039562b07229f39edb08c6519999b52fd6db8af3a5b9743c4f
3
+ size 4630580764