Hugging Face's logo

radi-cho
/
Meta-Llama-3.1-405B-FLUTE

Model card Files Community
Radostin Cholakov commited on
Commit
3a58b22
•
1 Parent(s): de1b5cd

Add nf_w4g64.

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. flute_config.json +5 -0
  3. generation_config.json +9 -0
  4. model-00001-of-00047.safetensors +3 -0
  5. model-00002-of-00047.safetensors +3 -0
  6. model-00003-of-00047.safetensors +3 -0
  7. model-00004-of-00047.safetensors +3 -0
  8. model-00005-of-00047.safetensors +3 -0
  9. model-00006-of-00047.safetensors +3 -0
  10. model-00007-of-00047.safetensors +3 -0
  11. model-00008-of-00047.safetensors +3 -0
  12. model-00009-of-00047.safetensors +3 -0
  13. model-00010-of-00047.safetensors +3 -0
  14. model-00011-of-00047.safetensors +3 -0
  15. model-00012-of-00047.safetensors +3 -0
  16. model-00013-of-00047.safetensors +3 -0
  17. model-00014-of-00047.safetensors +3 -0
  18. model-00015-of-00047.safetensors +3 -0
  19. model-00016-of-00047.safetensors +3 -0
  20. model-00017-of-00047.safetensors +3 -0
  21. model-00018-of-00047.safetensors +3 -0
  22. model-00019-of-00047.safetensors +3 -0
  23. model-00020-of-00047.safetensors +3 -0
  24. model-00021-of-00047.safetensors +3 -0
  25. model-00022-of-00047.safetensors +3 -0
  26. model-00023-of-00047.safetensors +3 -0
  27. model-00024-of-00047.safetensors +3 -0
  28. model-00025-of-00047.safetensors +3 -0
  29. model-00026-of-00047.safetensors +3 -0
  30. model-00027-of-00047.safetensors +3 -0
  31. model-00028-of-00047.safetensors +3 -0
  32. model-00029-of-00047.safetensors +3 -0
  33. model-00030-of-00047.safetensors +3 -0
  34. model-00031-of-00047.safetensors +3 -0
  35. model-00032-of-00047.safetensors +3 -0
  36. model-00033-of-00047.safetensors +3 -0
  37. model-00034-of-00047.safetensors +3 -0
  38. model-00035-of-00047.safetensors +3 -0
  39. model-00036-of-00047.safetensors +3 -0
  40. model-00037-of-00047.safetensors +3 -0
  41. model-00038-of-00047.safetensors +3 -0
  42. model-00039-of-00047.safetensors +3 -0
  43. model-00040-of-00047.safetensors +3 -0
  44. model-00041-of-00047.safetensors +3 -0
  45. model-00042-of-00047.safetensors +3 -0
  46. model-00043-of-00047.safetensors +3 -0
  47. model-00044-of-00047.safetensors +3 -0
  48. model-00045-of-00047.safetensors +3 -0
  49. model-00046-of-00047.safetensors +3 -0
  50. model-00047-of-00047.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/cl/scratch/model_weights/Meta-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": 16,
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": "float16",
32
+ "transformers_version": "4.44.2",
33
+ "use_cache": true,
34
+ "vocab_size": 128256
35
+ }
flute_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "num_sms": 108,
3
+ "num_bits": 4,
4
+ "group_size": 64
5
+ }
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": "4.44.2"
9
+ }
model-00001-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b90b4cfa9b9116b1fbe023029af06bd738e9401c5a2b9cd4c775397a5aebf5e
3
+ size 4987035088
model-00002-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f96765f8d8ab16d27d343b7aefb9cbf5a8ac184ecdbc509a5ab3e91da27393c
3
+ size 4670584640
model-00003-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e941fedd54acc9f540817c4d35f17dfae43461bb14b1cea39074311fb3a89b3b
3
+ size 4991448880
model-00004-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f046379ba85059e806e081a2eb4d0f2cdb6fad0540fd1a4883949f7dcfb8108
3
+ size 4955794296
model-00005-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e678f4d8a209cb2e887183bd5412763cf190ed4b10a70f7f323c199b70e68242
3
+ size 4670518920
model-00006-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4689f4ecf28146fa3d84bc269029ca06cd1e4f665f09e05921c24005324b0be6
3
+ size 4670584728
model-00007-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd4a6aff57a7e2bb4321fbe0ea164dd0efbd442ae6608bd2256a30f3382df8e
3
+ size 4670584720
model-00008-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d7be621c1976feae0b190eedcb2eb761f74be101ef50095e481e67091a43c9b
3
+ size 4991448968
model-00009-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a587e433c67127e4c96351eb91fe5d4cd5702e5fa106bbefbea1c59fde4f31c
3
+ size 4955794376
model-00010-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e85d4006b57a8caa05f77088d7f94dbd79b90b66de57b980529064fefb8c6a0
3
+ size 4670518952
model-00011-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f605a88d00bb076931e31031f94fe7c966b753135f5747aa70010d975e8ccec6
3
+ size 4670584728
model-00012-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:083f8825c875685b066e9e1940559b7c24b288698b43c806d3a9f8e1030a27c6
3
+ size 4670584720
model-00013-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0205707407cf8739010b981aa5f5c76e7ec67c48fa01f81da12ee168ae2bc98e
3
+ size 4991448968
model-00014-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:952e3cf60c47820b4575981968ddbe3f31b9a098c3501f6e259b57660d8580e5
3
+ size 4955794376
model-00015-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e6aa748eccf100a69f2355ce419f11fec54c2b0fd86031dc065343e454277a2
3
+ size 4670518952
model-00016-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2050eb9670e7bc5319e7891ffa3ed92534ce15f30463b639a7dec85623a7c363
3
+ size 4670584728
model-00017-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc0afa0bf1181b9579452093715260a89eb3962c969b6531d0db07b1d084ab9
3
+ size 4670584720
model-00018-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:280da8fa37ee398e759aab905bb0e3b8195660b2c6e8733075c994f15589275d
3
+ size 4991448968
model-00019-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f5b6e9cf64e296f97715b66fa4999b4674502d681f802baaacce6438c0b5268
3
+ size 4955794376
model-00020-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b20a61f0c7b6cbd165c215835dac1a1dccf0f02fa737ca4f2e714c1990be47e
3
+ size 4670518952
model-00021-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c31041007161db86edf9a402561b04349b00a9d933d589a1343cbbb2874c61f5
3
+ size 4670584728
model-00022-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440c9d766631ce86f6016ebf33f624178829e733057b3db1132cc690215a3dcb
3
+ size 4670584720
model-00023-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1128429c5b290edf8e6816727d6f74e1acc107d67286cf919ee027f5fe3be591
3
+ size 4991448968
model-00024-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be9e690b7ec42043ca301dc3204d7462cfd72a479ecc7a378ddbcd72a78dd11
3
+ size 4955794376
model-00025-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3aecd1128f4bd25e0859f28bd9459f2c25f1821ef82a3091a8d67e264e463e
3
+ size 4670518952
model-00026-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b02524e98d62050d021236fe9c3e347a48fb8416450832287fb777ac725d40
3
+ size 4670584728
model-00027-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c8649fbfc2478cce3c909ecfe4ba524fbaa3df8e3609d7fab32f974e0a2ae7
3
+ size 4670584720
model-00028-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635ce4ce984d4b5b0eae8c090384631b7798dbe486cef9d5bc9ce88ffacbed81
3
+ size 4991448968
model-00029-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c17a517546d32c618a7fe0d9e3ad9cf7aa1c77f557cbb899cafaa8f9e379f4d
3
+ size 4955794376
model-00030-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef22dac6503a20042c0444706c9712cbcc20eb57d196f01c473b8ec90ccdb93
3
+ size 4670518952
model-00031-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14c665902194578b36297b35cc1c8a0879f3240d0ec4fa1a5ae2ee101df60b8
3
+ size 4670584728
model-00032-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1619a1e4939385fcfa3bfc93b05ea99b6deeac1b6840266a584e613da05a179f
3
+ size 4670584720
model-00033-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd84216aef85ad1931d70f71ea7a4d2872eebcb4a3ea0619b82b2af80d3cf031
3
+ size 4991448968
model-00034-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a1e2c341e68f75ab492fb3b838b01cea0c0d7a3a326863f61f7da2b0cfb5556
3
+ size 4955794376
model-00035-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0f8932484a0cb740ee47e909b7734abbec5a0dc7a0f6b4b72b2da28eef8a0a
3
+ size 4670518952
model-00036-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35059acb555cbb0ac330e3cbc33e10656bad2850539a4f20a3916f606cb6592
3
+ size 4670584728
model-00037-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:786f4d544d97c7b58629fc4c3e9c0857c91cb6b7c9e03aad025f12ca45412486
3
+ size 4670584760
model-00038-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67a9e1e2d17822ca03333f13614814e4f3eb9abf4cb29cc9fccddeb5bd82c98
3
+ size 4991449056
model-00039-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d365794eb11fc2f13bff7a08f710851b3c0c6f03399926996a5259b883bf08cb
3
+ size 4955794456
model-00040-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f17873cb919a5bd70446cd00870077852a35f0d84d1afd7913240d84c4cc92
3
+ size 4670519032
model-00041-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ea41b8f9a8a2f6f53107ee8fdd9de6b983035f8a738b4e0000b3130c8b9020
3
+ size 4670584816
model-00042-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb88bfba7e2af768361242f0cb46bf8a3f8243c0d01593e3f5fbffe034fba4f5
3
+ size 4670584808
model-00043-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c3759e9589615dee40e5b8bcc2b87abe671445a4e6cf924eefe1f4aeedb4c5
3
+ size 4991449056
model-00044-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0defe1790900441fe2f5761bc0052e32f15d4994aee0e4643c4548ebd3f75b2
3
+ size 4955794456
model-00045-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:870e8926d4f1e413604117b11be72a11bcaf07e6a6a03c924d77bd679535833d
3
+ size 4670519032
model-00046-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44944b15fe4a6ba9e9a1da09b527521c4ad906cabdf2d740226ac0746c83919c
3
+ size 3886275304
model-00047-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad9f1b9d860e193110b25ae81706a93a93991adcd9e8b2333d3273235e6cee5
3
+ size 4202692736