Hugging Face's logo

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

Text Generation
Transformers
Safetensors
llama
llama-3.1
meta
bnb
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
1
mdouglas HF staff commited on
Commit
8b1cbed
•
1 Parent(s): 2427a06

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/base/base",
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": 8192,
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": true,
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 sha256:512d19aaf3b1811adf12649fd6585dbf17e96eda885d76ab37aea40f703b6d5e
3
+ size 4964329278
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a87128d152806d9d54a15ac1b5b218be1f0ec70ac650ac896a980dbb9a9b54d2
3
+ size 4985431347
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d35cefc87398b3436d1a82b97c2d0f53f4e40a5f7899f66b44bd809374006569
3
+ size 4985431344
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81efdd69e8f08783c15839b391de92e84f046e55d2e39c8e3df84d4890d4c8bb
3
+ size 4985431347
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd44523edfac729bf6c321e69081cad8412d27817327e962d5f67dc0dcebc67b
3
+ size 4985431449
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157fbf41f01981bb4f81d42d156bcb5339336a393f26da86fc30a8a5ce3c881a
3
+ size 4985431485
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0ae55b5ed497bcb934fcd02d4482691e6b1d3afb3b4a7b2c88af78064ab2aa
3
+ size 4985431487
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf3092cfc1d97d4a7fa6ccccf8aea22058737a7f1ab8bbed6900ed66e7ca503
3
+ size 4985431486
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e1d08b870325f89ec80f53eeb2e2eef2431091f08beafc9e7bdd45173cdc353
3
+ size 4985431484
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3ffed38ddf8f4742aa2d2396862d475e96dfef1c5b54181472d8227297db7be
3
+ size 4985431481
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7bb58a63141b09e76341c2d7ff80a0bae54311ef097fab354ecec84491eccb7
3
+ size 4985431483
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab13ac3a068a94907755d90759b37f9ac3a6dde98aef7328772e51170a499ce6
3
+ size 4985431479
model-00013-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da1c080ebcae50346496ea97773124313a75534124f71cf4a3ec0a56bde7cd43
3
+ size 4985431481
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41efd7ef8af0533bc1ab408f42dac8f870ce5218b054c0db4e0a855f6af3e095
3
+ size 4985431483
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0391df4b0edfead18b79948dcb146eb4024101178292370f35d726602ca73f72
3
+ size 4985431484
model-00016-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c1d58dae21056c75d167d8d4c60540fbb556d3e1a05e6e349f2bf32990ba81a
3
+ size 4985431478
model-00017-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db5cceda0477b9eddb12d48bfd23331bb0b7190c88259a11e5e5849ca6e3a2d
3
+ size 4985431480
model-00018-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:442f30d3799a7bf53b712ae339144db056ecc3d6be3476b834d83f68d452a7bd
3
+ size 4985431486
model-00019-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729ba50c57190906f6cc3d001aae841190f657bf5b1b3ee901f9eb81a62ac7b4
3
+ size 4985431480
model-00020-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aaa356114e7b9195e8b92b6f0162c69a3e8b48672d4a244d4062aa5228a67bb
3
+ size 4985431486
model-00021-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499f61170be126c026d79b5638b82c6d7aad35829a33f19a60686c89035fbfb8
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:ec2b6ea5af7a350e3ebafe5a80f1d701a9083978a187233045c0ff0636f39a44
3
+ size 4985431483
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98315f9184bc817c77e20719afd54c8510dc3ad70e18991d87ceb4bb07107aee
3
+ size 4985431480
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a90ce68e40b8b6aa346751f20b73b1022df5c7c4ccfe94e57dae7d11adb5c929
3
+ size 4985431481
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87adf7e0f42bf514fdac204dc0f02afeb257f77fd3fc6e9ca6944630ecd981ed
3
+ size 4985431481
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bfbd2e1a6a250ed0b5cfb3dc127fa01d1ef0be726bed522a3d29107e9338378
3
+ size 4985431484
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0569714bc477f11e0349d94af951331fb8123f5312505fff108820cccf86542b
3
+ size 4985431483
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c19ca555e618112383435e79d77fc373882d7a4ee1197506ed7ed0ed4edc68
3
+ size 4985431482
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e7c2a3f5137d11217a7b1d040aed46aad35123c2fb9b732dcd1e5258012eb1d
3
+ size 4985431483
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da01942e5fff040ee4e59fe583d52e30af09b0a919d1997f130068800c4930ae
3
+ size 4985431487
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c4b1223ca4a1932b84fd54e94f098543d4085aa7c44f2d2206bca1c27b8bcf
3
+ size 4985431485
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71969ae0d5180406d6d06972506f752db4c05216bf98b459eb1b3ba1377b6683
3
+ size 4985431486
model-00033-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3213b8236b6dac5336e7ce177f9b7532756c70a32dc7de83380e820a0d7dc458
3
+ size 4985431486
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309dd09ce5e7d8748527cac1bbfab642d579c8faf033be8b3a7f8d5e3aab85ea
3
+ size 4985431487
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ee9d066a90f5cd54923afc94b80aa3b4ff964a64996deb17c053b6979afebfc
3
+ size 4985431581
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b183e257a08d8c30097b7fc1b1560db2a5efbc510a35335d1e088160b886fc6b
3
+ size 4985431614
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f89694fb44108a1c89f8b1cd402f6fac9d5ed7ece9298483a71404dd0706bfa
3
+ size 4985431611
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d089704209212718d905f2dc6e3052a89076820eb9c8bb93ada5806ad14c610
3
+ size 4985431615
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:801ce2d8bc43b8c6dd950ed7ab5569c7bcc77014575bb99730d2f454cd808407
3
+ size 4985431610
model-00040-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:493b962c0a66330f89e58c0ac2d84636d887724be844141a4cfbe031ec7aab9b
3
+ size 4985431610
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acbe734f9c9d1b5ba5620f5e7b2b55368c50f4ededcb904f7f89e8a15511d933
3
+ size 4985431608
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9182e8f933666f0a24d2347f3b8e7db3b7aaa4e363230d90957cb7e0c7c5ecbd
3
+ size 4985431610
model-00043-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e5605c799dcbc67e51ffa40d207ef8203832e4a9c1b848ed975bfaea3e8e0c
3
+ size 4223827844
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19b417dcc7fd337f97811ce0cd49f33750240019dc873802e7e15b6ee63b428
3
+ size 4202692736
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff