Hugging Face's logo

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

Text Generation
Transformers
PyTorch
English
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
natolambert commited on
Commit
6bef6d4
·
verified ·
1 Parent(s): 7619b90

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 +35 -0
  2. generation_config.json +9 -0
  3. metadata.json +1 -0
  4. pytorch_model-00001-of-00191.bin +3 -0
  5. pytorch_model-00002-of-00191.bin +3 -0
  6. pytorch_model-00004-of-00191.bin +3 -0
  7. pytorch_model-00006-of-00191.bin +3 -0
  8. pytorch_model-00008-of-00191.bin +3 -0
  9. pytorch_model-00010-of-00191.bin +3 -0
  10. pytorch_model-00011-of-00191.bin +3 -0
  11. pytorch_model-00015-of-00191.bin +3 -0
  12. pytorch_model-00016-of-00191.bin +3 -0
  13. pytorch_model-00017-of-00191.bin +3 -0
  14. pytorch_model-00018-of-00191.bin +3 -0
  15. pytorch_model-00020-of-00191.bin +3 -0
  16. pytorch_model-00021-of-00191.bin +3 -0
  17. pytorch_model-00022-of-00191.bin +3 -0
  18. pytorch_model-00023-of-00191.bin +3 -0
  19. pytorch_model-00024-of-00191.bin +3 -0
  20. pytorch_model-00028-of-00191.bin +3 -0
  21. pytorch_model-00029-of-00191.bin +3 -0
  22. pytorch_model-00031-of-00191.bin +3 -0
  23. pytorch_model-00032-of-00191.bin +3 -0
  24. pytorch_model-00034-of-00191.bin +3 -0
  25. pytorch_model-00035-of-00191.bin +3 -0
  26. pytorch_model-00036-of-00191.bin +3 -0
  27. pytorch_model-00037-of-00191.bin +3 -0
  28. pytorch_model-00038-of-00191.bin +3 -0
  29. pytorch_model-00039-of-00191.bin +3 -0
  30. pytorch_model-00041-of-00191.bin +3 -0
  31. pytorch_model-00042-of-00191.bin +3 -0
  32. pytorch_model-00044-of-00191.bin +3 -0
  33. pytorch_model-00045-of-00191.bin +3 -0
  34. pytorch_model-00046-of-00191.bin +3 -0
  35. pytorch_model-00049-of-00191.bin +3 -0
  36. pytorch_model-00050-of-00191.bin +3 -0
  37. pytorch_model-00051-of-00191.bin +3 -0
  38. pytorch_model-00052-of-00191.bin +3 -0
  39. pytorch_model-00053-of-00191.bin +3 -0
  40. pytorch_model-00054-of-00191.bin +3 -0
  41. pytorch_model-00055-of-00191.bin +3 -0
  42. pytorch_model-00056-of-00191.bin +3 -0
  43. pytorch_model-00059-of-00191.bin +3 -0
  44. pytorch_model-00060-of-00191.bin +3 -0
  45. pytorch_model-00062-of-00191.bin +3 -0
  46. pytorch_model-00063-of-00191.bin +3 -0
  47. pytorch_model-00064-of-00191.bin +3 -0
  48. pytorch_model-00065-of-00191.bin +3 -0
  49. pytorch_model-00066-of-00191.bin +3 -0
  50. pytorch_model-00068-of-00191.bin +3 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.1-405B",
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
+ "hidden_act": "silu",
11
+ "hidden_size": 16384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 53248,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 128,
18
+ "num_hidden_layers": 126,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "high_freq_factor": 4.0,
25
+ "low_freq_factor": 1.0,
26
+ "original_max_position_embeddings": 8192,
27
+ "rope_type": "llama3"
28
+ },
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
+ }
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": "4.43.4"
9
+ }
metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_name": "405B_finetune", "model_type": "sft", "datasets": ["allenai/tulu-3-sft-mixture"], "base_model": "meta-llama/Llama-3.1-405B", "wandb_path": "https://wandb.ai/ai2-llm/open_instruct_internal/runs/2ie8o91c", "beaker_experiment": "https://beaker.org/ex/01JFFWHSE3QQZYPFV4VK5JDM5D/", "beaker_datasets": ["https://beaker.org/ds/01JFFWHSFN1R29S4X5DG3CRH9T", "https://beaker.org/ds/01JFFWHSMXF63ANG73RJ54M5EP", "https://beaker.org/ds/01JFFWHSSQ6H2WJRQMTTQVHEDA", "https://beaker.org/ds/01JFFWHT04VR436TVND8S72QQS", "https://beaker.org/ds/01JFFWHT5R1MSD44EZJ54YT7WQ", "https://beaker.org/ds/01JFFWHTB1GZF03V5XNHS4T4YJ", "https://beaker.org/ds/01JFFWHTGQADM2B3DRABYXGQCG", "https://beaker.org/ds/01JFFWHTNYQAJ3M823ZXARMMVA", "https://beaker.org/ds/01JFFWHTVJ4CCZB8ES6TYYXM8T", "https://beaker.org/ds/01JFFWHV105QRDFHZK78E7ASW8", "https://beaker.org/ds/01JFFWHV6K1HKYQXSNXZ1TGQNY", "https://beaker.org/ds/01JFFWHVBNFVXDT12KX4VAND3P", "https://beaker.org/ds/01JFFWHVGWVVRTXHV5RQNCASN1", "https://beaker.org/ds/01JFFWHVNYCZ8JNYW6HMNVS53H", "https://beaker.org/ds/01JFFWHVV759YDWYE3SB0Y5ZWA", "https://beaker.org/ds/01JFFWHW0C60STRSFGYS7EXDB5", "https://beaker.org/ds/01JFFWHW5VXWAY8TGBAPQ057NH", "https://beaker.org/ds/01JFFWHWB4KZEQ9NZC47JB41JE", "https://beaker.org/ds/01JFFWHWG94B463B0WMH1958EA", "https://beaker.org/ds/01JFFWHWPKX234EHP8BG956THX", "https://beaker.org/ds/01JFFWHWVWYN94MG7FT3210FJ0", "https://beaker.org/ds/01JFFWHX0MVZV5GRWE2NZR36NM", "https://beaker.org/ds/01JFFWHX5STFAZZ3VW83A2CGNE", "https://beaker.org/ds/01JFFWHXAQF4VM5SDA8XMM56E2", "https://beaker.org/ds/01JFFWHXG58THFNR24J1PS96BK", "https://beaker.org/ds/01JFFWHXNCXQBMDZFW0A4NRCBK", "https://beaker.org/ds/01JFFWHXTYDW6AKN6120BGC4TD", "https://beaker.org/ds/01JFFWHY005EFTYRF4R8FRTACD", "https://beaker.org/ds/01JFFWHY586FNKX5KTE8F4S9W8", "https://beaker.org/ds/01JFFWHY9ZPGW3FANWD8DKNWM0", "https://beaker.org/ds/01JFFWHYF6BCVFGR11J1ARCZT5", "https://beaker.org/ds/01JFFWHYMRM90CB2KGQVJJTDCR"]}
pytorch_model-00001-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53addc97eee60ea60ead2a03392c388368819933bb63b2b6cf8a1719ddcce4c
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 sha256:20ed06f1ff913cdff95503883f4530101704eb6e7fae9fd4d9f9fbcc44e18bcf
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 sha256:9bcbcd0b25892192dd4216876c007f6297d036a20a5d2f79b326b2ea85596b98
3
+ size 4630580764
pytorch_model-00006-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d6b28b9d23719485136ba1ca3f1b480bf7e7abef30312037becc6b37b25e82
3
+ size 4630580764
pytorch_model-00008-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1dfefc24aafd05f09b257ceebd73925e75ab7b7da94b246d1495b0c928c0c1e
3
+ size 3489662678
pytorch_model-00010-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:290e8ec621c429efbbdfc0f7681b4374e5825574fc03acdd63f36d0c39377a4b
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:d65ae3ac4e84e63cc24e3a9f62d1e7631d6fa78a9aee83556f085d0deab551ab
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:ff3da16df3f07d61ffd56dd9dbc3994377261b040bf2e86a6c9f02a5b2eabbc7
3
+ size 4630580764
pytorch_model-00016-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75bb5d2754cc8eb1a16657123eb9bab8078ffb48f87f626ab2f8af01f0f0e87a
3
+ size 4630580764
pytorch_model-00017-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39ef03e0e15ae5205144df08d50cc4106daad0576f493367bcff3ab9b2d6724f
3
+ size 3489662678
pytorch_model-00018-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab0f678a5de50201ed4d31ad6166d2295699f4b9554c177c8f60cd5ada76a7f1
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 sha256:095e68cb4711c8dcda664292d3fb447e0d88ffb8a6261c9eaa9611686b1c8ecf
3
+ size 3489662678
pytorch_model-00021-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6689adb4d668662ca0765f716f9ca6a473944b0b452ee6c424395a24dd96bfff
3
+ size 4630580764
pytorch_model-00022-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc83dec3db6dee67357c13f6526e4f078491c363b84a1b4d217b85e22709a009
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:e3bcc71e6f94df1ea2bb1a9ce4d6e6e9ad95eebe5734e5c27d891519732925bf
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:f270569affa6f4882ebe9f5e3503666374ed8b97a99e9b469006d92a50ef6eb8
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:f375e9163c7add7189e8f8bb0786e27d418e648e292042fba34a4bf615a41cca
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:ff507d3edbf2b00f3e807f286a99bbae9e28fbc6b568d7b7bb17905de37fd230
3
+ size 3489662678
pytorch_model-00031-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf59d1f739e3483695b0d77d2e3fbc62aae4d4d4acaa031cdcf3dc2b701a477
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:fdbec47d25cea65b4e3f98c5236eae16ec2dd8da66de4dc336289fa515783488
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 sha256:911c9cc9ec96475d9bb179a000b7d16d8ad4423aeedcebad3966bc6b7ceac2f3
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 sha256:398a293658ce436d38c6178508e26126685a54826c3aeb7238ba2cdb57438865
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 sha256:66ef6373f4ad3a772b88fc4c8b256d2695ab29b95c17afb1ed68d1fc4fc3f458
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 sha256:2148c944581cd9d20eb33f979881c8682f567e01ecc747d69af6b480dfc76196
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 sha256:786981ae866db664dd14d655f39b0c5f0420c463ad9450de088bceda90af8524
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 sha256:8ec157f8c1227cf24c55c8c678512c2e0817a5602c08c79aaf180a6560b33a6e
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 sha256:97a94dcd4ff652d55890081855c429409a4bf15a6617a31a15740f2fed392b3f
3
+ size 3489662678
pytorch_model-00042-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97a1b97085a581e0df5b7a39bb4dc28ee78a4b121de9931732ba5501068acf7d
3
+ size 4630580764
pytorch_model-00044-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a3f769f9c072ec5d312bceedfa671ef2309f8b6d9df3803103246d5854ddab
3
+ size 3489662678
pytorch_model-00045-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a727951592b07d0d56a727676a3d245e98dd88bf815c1274ae6da700713c234a
3
+ size 4630580764
pytorch_model-00046-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f090b7067d4d499801eaf8f9e5b764241b1be7187d6eb7e43b55587e78e19f43
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 sha256:077779c610212eb30ecc278a013773675e67400e0c362796175b4819f0172bf4
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 sha256:8bd4f0a83b10c5317e2ce5e2479afe9d8bcdae3a80813f36aaba3594da7db383
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:e1cbbad9ce6ec2ac7fa5cc8ac21d8c7142a13d52535e38f674a3483718254dd7
3
+ size 4630580764
pytorch_model-00052-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f8a224df6dc8aea3deda35ee2db2a70287386213cdf06cf9686d3ac501dc4dc
3
+ size 4630580764
pytorch_model-00053-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d9b2d1a59618968903d278c589bad75db77708ace246d82edd137b1d02d185
3
+ size 3489662678
pytorch_model-00054-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3eae6acd85eedd8ba70e77382a4227aa5fc32bc3bc3563ce13e45023540ea05
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 sha256:91d058c05ae0d7145746916c0d17158a110637e45530629e70309d94d1843ab9
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:dc0f6b7f23ab606741d1a5ef4aac8511ef587aeeb99b1083fc0b49347ddf8e0d
3
+ size 3489662678
pytorch_model-00059-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba1fdb5c6cfd710817d06484a6bedc82526406da56f805f9288bc59211ca9bf0
3
+ size 3489662678
pytorch_model-00060-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c9c5627b6f229d0d70a6569328f6de6adeb426cf925207db468bfee47805542
3
+ size 4630580764
pytorch_model-00062-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9817a184c6cae8bbb4b32bd86166a7a8219cc81c0f13bbc5233d5a995c628996
3
+ size 3489662678
pytorch_model-00063-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b9f4fbd9022a13e2f6f5d668c2764bca4f6c6fe5fc2cb91711bc6b2665ecd3
3
+ size 4630580764
pytorch_model-00064-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41b4d751d6ec7c74ff960a0044f1390790cac94d035266c926a8e4a16676162
3
+ size 4630580764
pytorch_model-00065-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d217fb3735aa8f287b7d786461dc1e2d5e370ce3fcd450911be11a4c7d077c1
3
+ size 3489662678
pytorch_model-00066-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd1a54e7cff88bf7609cc7de4583898f1484f4bb246e67634ed1529cb3673d3
3
+ size 4630580764
pytorch_model-00068-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5edcc537710c6c81acfaf2b7bd95ed2845654555d2136403422dd889a077d4a1
3
+ size 3489662678