Hugging Face's logo

hugging-quants
/
Meta-Llama-3.1-405B-Instruct-BNB-NF4

Text Generation
Transformers
Safetensors
8 languages
llama
llama-3.1
meta
bnb
conversational
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
2
mdouglas HF staff commited on
Commit
49f9feb
•
1 Parent(s): d856fa9

Upload folder using huggingface_hub

Browse files
Files changed (47) hide show
  1. config.json +44 -0
  2. generation_config.json +6 -0
  3. model-00001-of-00044.safetensors +3 -0
  4. model-00002-of-00044.safetensors +3 -0
  5. model-00003-of-00044.safetensors +3 -0
  6. model-00004-of-00044.safetensors +3 -0
  7. model-00005-of-00044.safetensors +3 -0
  8. model-00006-of-00044.safetensors +3 -0
  9. model-00007-of-00044.safetensors +3 -0
  10. model-00008-of-00044.safetensors +3 -0
  11. model-00009-of-00044.safetensors +3 -0
  12. model-00010-of-00044.safetensors +3 -0
  13. model-00011-of-00044.safetensors +3 -0
  14. model-00012-of-00044.safetensors +3 -0
  15. model-00013-of-00044.safetensors +3 -0
  16. model-00014-of-00044.safetensors +3 -0
  17. model-00015-of-00044.safetensors +3 -0
  18. model-00016-of-00044.safetensors +3 -0
  19. model-00017-of-00044.safetensors +3 -0
  20. model-00018-of-00044.safetensors +3 -0
  21. model-00019-of-00044.safetensors +3 -0
  22. model-00020-of-00044.safetensors +3 -0
  23. model-00021-of-00044.safetensors +3 -0
  24. model-00022-of-00044.safetensors +3 -0
  25. model-00023-of-00044.safetensors +3 -0
  26. model-00024-of-00044.safetensors +3 -0
  27. model-00025-of-00044.safetensors +3 -0
  28. model-00026-of-00044.safetensors +3 -0
  29. model-00027-of-00044.safetensors +3 -0
  30. model-00028-of-00044.safetensors +3 -0
  31. model-00029-of-00044.safetensors +3 -0
  32. model-00030-of-00044.safetensors +3 -0
  33. model-00031-of-00044.safetensors +3 -0
  34. model-00032-of-00044.safetensors +3 -0
  35. model-00033-of-00044.safetensors +3 -0
  36. model-00034-of-00044.safetensors +3 -0
  37. model-00035-of-00044.safetensors +3 -0
  38. model-00036-of-00044.safetensors +3 -0
  39. model-00037-of-00044.safetensors +3 -0
  40. model-00038-of-00044.safetensors +3 -0
  41. model-00039-of-00044.safetensors +3 -0
  42. model-00040-of-00044.safetensors +3 -0
  43. model-00041-of-00044.safetensors +3 -0
  44. model-00042-of-00044.safetensors +3 -0
  45. model-00043-of-00044.safetensors +3 -0
  46. model-00044-of-00044.safetensors +3 -0
  47. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/scratch/llama405b/instruct",
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": 16384,
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
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "bfloat16",
25
+ "bnb_4bit_quant_storage": "uint8",
26
+ "bnb_4bit_quant_type": "nf4",
27
+ "bnb_4bit_use_double_quant": true,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": true,
33
+ "load_in_8bit": false,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_scaling": null,
38
+ "rope_theta": 500000.0,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.43.0.dev0",
42
+ "use_cache": true,
43
+ "vocab_size": 128256
44
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": 128001,
5
+ "transformers_version": "4.43.0.dev0"
6
+ }
model-00001-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1011f343f704c1252e6afd72f10fe3e8a0355be1cf046c608ee1cc3cc663885e
3
+ size 4964329279
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498d049d6e56eb75ce131b03f821d4f6a2fdaad365dc660bafba549ce61d1d88
3
+ size 4985431350
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9abcb1f31dfcf2c33f3a9a3ea4e03307f7b30b7c50a8744bbd38800f48e247dc
3
+ size 4985431350
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58d32014c8847c59be16f59f7c5132478a34a6a32ff3f267cadec006948dd34b
3
+ size 4985431348
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49102a06093d80eaec75a1e7756d435eac2573e9b1a1be9ba1d8d17afb0f59dd
3
+ size 4985431453
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e6f505f9dbc0a7640b2a8106959fb9a68385942538ec38da005471b94285b2
3
+ size 4985431485
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4c8efd280072672f7bfab46a3ebd2754c87f6ae75a665fa4b5998026794e2c
3
+ size 4985431486
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e4eeba22ac95038bc71ac40c71bd53b21498c46bc900f6ba978923dfd2841e
3
+ size 4985431481
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854428e8d26df2266f56be7ba9117d12113845cb2c2c375d942154fb3becced5
3
+ size 4985431487
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b961596be5008d4273ce142c5b4bd4d1e968410e496c8db949634580bf438e
3
+ size 4985431482
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66c50b4d87c932aba52bffe29723ca4267b9c3951f9a8d2209cae23615c6842
3
+ size 4985431482
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:328ad2f7613f5562b269d75492590804d82ddef6a6ce11bea1726cd1f9f7df50
3
+ size 4985431486
model-00013-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dded8d52beaa110171eb5b62133540b6aa9fa27d3bf4205f2891686f56f9587
3
+ size 4985431486
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa91dfaec89f0d63934a9fe8a8f27c9e2221d971e0e7ae049a7f5d63ecab2b2
3
+ size 4985431482
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdce11c7044e249550dd37ed727a90873c304c04cf03e4741ded62eeceaaa0e5
3
+ size 4985431483
model-00016-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e59bf2a0c90a5f1b48a8b2ec4f885447631376b6fa53839bb7559227877c3f
3
+ size 4985431486
model-00017-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61632d8b6436047ec6d08fddf3a7a3d4f8abe589577d8b61af7c11ad8755e862
3
+ size 4985431489
model-00018-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f5a50096676593b7a12e90845de68a796babcb225316662d3d527571ddd470
3
+ size 4985431476
model-00019-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a79850ab9d1abeb116e7b3794a59503e6eec2f8472f6b0207745274c4f116d4
3
+ size 4985431480
model-00020-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f8a88c04c0836c2854fa1350e14f69ed6aa71d7acc582bb40570fc53ef6eb55
3
+ size 4985431484
model-00021-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b466c84949e69dbc1584b2d27d3c43d6f8124fe2b780bbbe39b67d35911e4c4
3
+ size 4985431482
model-00022-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde668903f4bd7ee59542dbf594f36e133dba288e413fe4a4f0e13ada980d0f5
3
+ size 4985431483
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76b676e11da9647d391b86a5443fa8e15b40a0acea980af396d4e74c670b1cc9
3
+ size 4985431487
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119a0f0f0711405e05fb2f0706e8b3d652a51cd6ea72cb1af00014f74466c4e9
3
+ size 4985431481
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c503887bd10b4e03737edd4e8fdf9f1b4b122a2ecb710f08f2f86de249ffe9fd
3
+ size 4985431483
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e4c497499e5efcd5c06e9da76edde767376869e6ba1c34372825e5f4ce31e15
3
+ size 4985431480
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ac0bb8bc97bb51bcb2923dd470e1f37ffda8dc7bfe1fabe046f4f48ba1861c
3
+ size 4985431482
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2a1d3da9a49cb0d7e9504333eaef8327384de2e67a10de343e10a23d47c4d9a
3
+ size 4985431480
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81808e9cf51d4c3245525395076c73f8c164ca4c365f150aaab4800db692a61
3
+ size 4985431487
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e43c9b91940c1439d99d4f7427f808ccd8873f2ada4eb4cfee98b4536e427da
3
+ size 4985431484
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f10f7ea1ca0419aaa0bbffdef8c80a57a26fc87c0e34ec18e61c1b35f2c3a1c
3
+ size 4985431477
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e28031034350fade63c6877305165360bf304443c49ad27a625497cf95f5924
3
+ size 4985431483
model-00033-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41f7bbd5c8eba250bedf2f70a989d5fa35779aa719af9f4430b6d6518546d2b
3
+ size 4985431487
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc2793370231e248b30c7f04a66bf663ab4ceb61ff4f59693de0c18c1d5035b2
3
+ size 4985431479
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccdd8ef52d939c2de1c0ab4cd40ce6423c06d2174c58e50f0c7a99628701f89f
3
+ size 4985431584
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8247fb20ca317756fe2bb4a56d2366fd9e70bf500a6759ef3d40b4106932ed3
3
+ size 4985431612
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e314b23160dc9eb6c95722567d6e3a437a78bf2989e86fa6dfd3c850417796e
3
+ size 4985431615
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536c1e7b66b776c2aa1f3870722c6751f103e3b1a097a7b850c9ec58476f1c25
3
+ size 4985431611
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:903f18d5390b043f4eb4b59f651edb258460508555080f5b5de98e8eb8208a3f
3
+ size 4985431612
model-00040-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0297dafd41238c600b9677b47721b2bf36b3a15aa6a36859d149896be3854939
3
+ size 4985431612
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfede9e7c1693b1905e56eba86b33e65a3534f8b5e5233b633f7c77a0a29892c
3
+ size 4985431608
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0ebc0be33c726065ea854773a3619e954d75ba6dc9f03f39460bb27f874a7a
3
+ size 4985431609
model-00043-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b6ff49b85a547b9e3525683d746cf36fa7c345798fcbd3bf40934439aa69398
3
+ size 4223827847
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71b079a02069ebe5a5f4f8135815f136afb1d6fc4423620dcb2a14fa399cdf12
3
+ size 4202692736
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff