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
1f903a5
·
verified ·
1 Parent(s): 5d05808

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-00004-of-00191.bin +3 -0
  6. pytorch_model-00007-of-00191.bin +3 -0
  7. pytorch_model-00008-of-00191.bin +3 -0
  8. pytorch_model-00009-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-00012-of-00191.bin +3 -0
  12. pytorch_model-00013-of-00191.bin +3 -0
  13. pytorch_model-00014-of-00191.bin +3 -0
  14. pytorch_model-00015-of-00191.bin +3 -0
  15. pytorch_model-00017-of-00191.bin +3 -0
  16. pytorch_model-00018-of-00191.bin +3 -0
  17. pytorch_model-00019-of-00191.bin +3 -0
  18. pytorch_model-00020-of-00191.bin +3 -0
  19. pytorch_model-00021-of-00191.bin +3 -0
  20. pytorch_model-00022-of-00191.bin +3 -0
  21. pytorch_model-00024-of-00191.bin +3 -0
  22. pytorch_model-00025-of-00191.bin +3 -0
  23. pytorch_model-00027-of-00191.bin +3 -0
  24. pytorch_model-00028-of-00191.bin +3 -0
  25. pytorch_model-00029-of-00191.bin +3 -0
  26. pytorch_model-00030-of-00191.bin +3 -0
  27. pytorch_model-00031-of-00191.bin +3 -0
  28. pytorch_model-00032-of-00191.bin +3 -0
  29. pytorch_model-00033-of-00191.bin +3 -0
  30. pytorch_model-00034-of-00191.bin +3 -0
  31. pytorch_model-00035-of-00191.bin +3 -0
  32. pytorch_model-00037-of-00191.bin +3 -0
  33. pytorch_model-00038-of-00191.bin +3 -0
  34. pytorch_model-00039-of-00191.bin +3 -0
  35. pytorch_model-00040-of-00191.bin +3 -0
  36. pytorch_model-00041-of-00191.bin +3 -0
  37. pytorch_model-00042-of-00191.bin +3 -0
  38. pytorch_model-00043-of-00191.bin +3 -0
  39. pytorch_model-00044-of-00191.bin +3 -0
  40. pytorch_model-00045-of-00191.bin +3 -0
  41. pytorch_model-00046-of-00191.bin +3 -0
  42. pytorch_model-00047-of-00191.bin +3 -0
  43. pytorch_model-00048-of-00191.bin +3 -0
  44. pytorch_model-00049-of-00191.bin +3 -0
  45. pytorch_model-00052-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
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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": "dpo_tune", "model_type": "dpo", "datasets": ["allenai/llama-3.1-tulu-3-70b-preference-mixture"], "base_model": "/oe-adapt-default/costah/models/405B_finetune_successful", "wandb_path": "https://wandb.ai/ai2-llm/open_instruct_internal/runs/i37wmors", "beaker_experiment": "https://beaker.org/ex/01JGHPDK13NRHFYVB63HX2CA2N/", "beaker_datasets": ["https://beaker.org/ds/01JGHPDK2SBMMK4J9XC4KD6N5M", "https://beaker.org/ds/01JGHPDK80YAWX0DCQBXWWGA3K", "https://beaker.org/ds/01JGHPDKDDFCVWK3XFZDE64619", "https://beaker.org/ds/01JGHPDKKB6YXHPZJ2J6P7BBX4", "https://beaker.org/ds/01JGHPDKS1X2M28ZMXQ82RXYMZ", "https://beaker.org/ds/01JGHPDKZ61Q19WZMVQ7F2NB95", "https://beaker.org/ds/01JGHPDM4WYBM6T47AEKAPEKHQ", "https://beaker.org/ds/01JGHPDM9P07DR389FS1RNE3RQ", "https://beaker.org/ds/01JGHPDMEY98RGPZZ8XSKN4Z3Z", "https://beaker.org/ds/01JGHPDMMGWB0PGE26XVS8PHW6", "https://beaker.org/ds/01JGHPDMSZ5RFE2SGNJHE96X7G", "https://beaker.org/ds/01JGHPDMYWT1HBN2EX5GEHEBMS", "https://beaker.org/ds/01JGHPDN3TAH804M0NCR2A312M", "https://beaker.org/ds/01JGHPDN9825E5QK0C0XERXRNE", "https://beaker.org/ds/01JGHPDNEGV7CC6D4RF6Z6MA97", "https://beaker.org/ds/01JGHPDNK8NX41YFMZRC3KHAEF", "https://beaker.org/ds/01JGHPDNR8B7AFA6E0K5CVAG6V", "https://beaker.org/ds/01JGHPDNX6MWX0VANCPBA134XR", "https://beaker.org/ds/01JGHPDP1XJA0CN35SG3D2907F", "https://beaker.org/ds/01JGHPDP772GZGYRH33SHAXPPY", "https://beaker.org/ds/01JGHPDPCREM04ZWA4RFDMWH20", "https://beaker.org/ds/01JGHPDPHMED877NVTCAYH28E1", "https://beaker.org/ds/01JGHPDPPHGKA4YWPTVJHVCQ6V", "https://beaker.org/ds/01JGHPDPVFM1N9ACMMXJEXMJ8Y", "https://beaker.org/ds/01JGHPDQ0GYFD165CCEVPGKS5W", "https://beaker.org/ds/01JGHPDQ5TH02BJ1V79Z010R8F", "https://beaker.org/ds/01JGHPDQBKPXTSFNWVQ7D59W93", "https://beaker.org/ds/01JGHPDQGW6V8FZB2S4G45ZDND", "https://beaker.org/ds/01JGHPDQPJ9G3ZFEVTESN71N2H", "https://beaker.org/ds/01JGHPDQW2KXXJK55E3YDYXVQM", "https://beaker.org/ds/01JGHPDR1K2DXGT5TRG1RGRSD2", "https://beaker.org/ds/01JGHPDR6H891W7A5Q8PY0NYYV"]}
pytorch_model-00001-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb021606598ef203f5926e0e63a80044b819329ffd946a67cf51d4cbf982c18
3
+ size 4806936944
pytorch_model-00004-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5493b03216a4b1c8a2b0467910ea94be6c0f0fa9df46bfc4516e92145491c44a
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:a6be60da0a41ae4172d064ace739b9a8f76bc0a828c0a745e34bc51b14075114
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:def6e67212d3d4e01b21689ac10a91e168f041a0ca78f37961efdb0765ce8c7f
3
+ size 3489662678
pytorch_model-00009-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae2f308974f319f15a1c079a68daa9f3ac8d303952c0d8e3adfa2e92a460145
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:f1db97dfae55fd36c8be1e7f932b47957861eb136f6c4c2469d1d45d2cf0e028
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:d223a24303662ba2d66467acbc6186b57657722bfdf3dd57a4675bde1ac25636
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 sha256:3dcf933a703df5d7e62419cb31c6ef12ce8cd34e88980bf4703abec5b9c5b01a
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:b6283902be92f8e5caee293272fd13b4b2499c49a05a7b40678bd98f40872f42
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 sha256:2d07b553de21bcb954bb0f17c649de7436e57a53025088dd7aec6d6973d5c7e7
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 sha256:7b0b68ff499f315ab56713afd2b921901adda7cbc5f37639a530432c9f0a0e5d
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 sha256:7fa2456bd28829fa98d2af7ab3f9317179032a90fe907975f82dded0b4f4c7f2
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 sha256:2048fa279d6277c4577b4787ada4a38830c8c2aeed97c89f66e542ea1e6ce49f
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 sha256:3a7176a88c6eec3d9e92676acaa6e6fb42bdeb829818be17c8e5068a6e5686b6
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 sha256:35c2dfdf7741c2c1168b54efe1c14eaef7c706cab89a3b41bfa8842fcba2195a
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:ec21a045887faf164e87a378288096561ceaab1a29bb9b08487572f17f8dc7fe
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 sha256:3f31b09e1789d69ec5d4daeab07e086833c354554396a8b542a1d90e12496114
3
+ size 4630580764
pytorch_model-00024-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ccdad499aa17754d81d46b73d7543e4f6f96e8a237d7a76628b884ee744a6b
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 sha256:2f1e8f8cca1b28b82e3a631e4ade726b25d5b28362f3bd05efdbcd09d2a25cc4
3
+ size 4630580764
pytorch_model-00027-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5ec245fd0a79a4d00e40b4c053c0042c9ed252d5d98d4ce07630df27cceaca7
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:bbd70bf3f2bc4bbe3caf709d93a84c475cb991d4e11ea914e77abfbcf4d06df7
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 sha256:3e029409361c1e4db0556845e35b48f9dd42488a0d4fc47d1784a97e50080bd4
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:ecf8299c91629fd2f14ce1232f0f02e930d89dce111f00aef32b01bdcde94a13
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 sha256:504a08849ea866c848f865bf688a5e8557577df607b8e524636cf3a304db8ce6
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 sha256:1d247c22a539a7e2d05835a09f25627ad9192337226dec071a7a334f077bcf49
3
+ size 3489662678
pytorch_model-00033-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d81cd58483bf70156a279bc5e65701ab63605270afdaa8e3a898f921aaa704ea
3
+ size 4630580764
pytorch_model-00034-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93bccc9b757e498a9da9e89e3ce69a78ae4d82d7cc15974e7af50f3c88ff6695
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 sha256:6f633b8471b88c773fc29a28cf55c7f555dc30e65b2b0a3bd987349ef5fead6e
3
+ size 3489662678
pytorch_model-00037-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac30e3499750086940bd0482ab80c7bea7c87b6ac5de0f46d2f16a2aee3ce98
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 sha256:006bc29fe6162d47ebb25db9cbb1eaa1bc89be9499aca191c9db93624c57cf7c
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:da4cec21a5fdb2773df85ed98f4de81ea71a9b3247e863ca46700bfadfb4304a
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 sha256:84638fbb51eebea312d86d9f1a22f9bdbaba1a6478277fe0d68c1a7dc4be62b0
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:cec7de932e1d997eb77d6fdb44991a99a90d31cf9f60c8cf07844d8a7079aa7a
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 sha256:42eecb307b84fab58bf8d4f77d94e61165e669236a59ded81bc30ebe5111e0e1
3
+ size 4630580764
pytorch_model-00043-of-00191.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dddcaaf64d409f99d4110a16277049d151af1799b3a8e171442fa30bd81e61d
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 sha256:978543027194d76e974d88760fa899c1b876ea2254ba62aee35417563efdfdd4
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 sha256:22c3cef4ec589c0a55799db81b573eb927c7508a9e36f42d669e3c2eeabf5b30
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:fff2b468cbd1f7ae52675122be2be38cf9fcb2fc0e9da5f8b3b656e2bd0c36ee
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 sha256:77273328a71c4fc95527cf678c1585b734640f267751335278bd957beb6670aa
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:d7c0b8f771246b8dab724cd6b4ecc4b5afc2a3f881720217bd4c970195792cd7
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 sha256:3cd511948d6449063f1b7d94d8a0280fecc6fb0c35909d326c1d682b50956b97
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 sha256:9fc981ae7b6ad0261c1a58012eeceb6294a21520259040cd8741332fb21f73f8
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 sha256:78a1782b2dde0ef1115990c55ac63ca5528b4cd1b41e9f39d09670a82cd3a1cb
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:c82b4722b086a55fd06f40aacf97bc8ef86ad3580f8316fed32aa052833218cb
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 sha256:0e77ac9bb06b97f14d2974c31d722b6a7503726be316564e7f1e4a89914c96da
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:ffc576b31d4e60fa56ac6bcb15dcb95c1abb23170e9eebf4eb38cb4dd783f764
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 sha256:315adbabd5ed6fd8dcc11c0a9fbff846adecf4b9838c5efd39ca9ba3bda74a73
3
+ size 4630580764