Hugging Face's logo

Dongz
/
llama31-405b-quant

Safetensors
Model card Files Community
Dongz commited on
Commit
5eef9d8
•
1 Parent(s): 837c353

init

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. awq_w4a16g128/real_quant_model/config.json +39 -0
  2. awq_w4a16g128/real_quant_model/generation_config.json +12 -0
  3. awq_w4a16g128/real_quant_model/model-00001-of-00047.safetensors +3 -0
  4. awq_w4a16g128/real_quant_model/model-00002-of-00047.safetensors +3 -0
  5. awq_w4a16g128/real_quant_model/model-00003-of-00047.safetensors +3 -0
  6. awq_w4a16g128/real_quant_model/model-00004-of-00047.safetensors +3 -0
  7. awq_w4a16g128/real_quant_model/model-00005-of-00047.safetensors +3 -0
  8. awq_w4a16g128/real_quant_model/model-00006-of-00047.safetensors +3 -0
  9. awq_w4a16g128/real_quant_model/model-00007-of-00047.safetensors +3 -0
  10. awq_w4a16g128/real_quant_model/model-00008-of-00047.safetensors +3 -0
  11. awq_w4a16g128/real_quant_model/model-00009-of-00047.safetensors +3 -0
  12. awq_w4a16g128/real_quant_model/model-00010-of-00047.safetensors +3 -0
  13. awq_w4a16g128/real_quant_model/model-00011-of-00047.safetensors +3 -0
  14. awq_w4a16g128/real_quant_model/model-00012-of-00047.safetensors +3 -0
  15. awq_w4a16g128/real_quant_model/model-00013-of-00047.safetensors +3 -0
  16. awq_w4a16g128/real_quant_model/model-00014-of-00047.safetensors +3 -0
  17. awq_w4a16g128/real_quant_model/model-00015-of-00047.safetensors +3 -0
  18. awq_w4a16g128/real_quant_model/model-00016-of-00047.safetensors +3 -0
  19. awq_w4a16g128/real_quant_model/model-00017-of-00047.safetensors +3 -0
  20. awq_w4a16g128/real_quant_model/model-00018-of-00047.safetensors +3 -0
  21. awq_w4a16g128/real_quant_model/model-00019-of-00047.safetensors +3 -0
  22. awq_w4a16g128/real_quant_model/model-00020-of-00047.safetensors +3 -0
  23. awq_w4a16g128/real_quant_model/model-00021-of-00047.safetensors +3 -0
  24. awq_w4a16g128/real_quant_model/model-00022-of-00047.safetensors +3 -0
  25. awq_w4a16g128/real_quant_model/model-00023-of-00047.safetensors +3 -0
  26. awq_w4a16g128/real_quant_model/model-00024-of-00047.safetensors +3 -0
  27. awq_w4a16g128/real_quant_model/model-00025-of-00047.safetensors +3 -0
  28. awq_w4a16g128/real_quant_model/model-00026-of-00047.safetensors +3 -0
  29. awq_w4a16g128/real_quant_model/model-00027-of-00047.safetensors +3 -0
  30. awq_w4a16g128/real_quant_model/model-00028-of-00047.safetensors +3 -0
  31. awq_w4a16g128/real_quant_model/model-00029-of-00047.safetensors +3 -0
  32. awq_w4a16g128/real_quant_model/model-00030-of-00047.safetensors +3 -0
  33. awq_w4a16g128/real_quant_model/model-00031-of-00047.safetensors +3 -0
  34. awq_w4a16g128/real_quant_model/model-00032-of-00047.safetensors +3 -0
  35. awq_w4a16g128/real_quant_model/model-00033-of-00047.safetensors +3 -0
  36. awq_w4a16g128/real_quant_model/model-00034-of-00047.safetensors +3 -0
  37. awq_w4a16g128/real_quant_model/model-00035-of-00047.safetensors +3 -0
  38. awq_w4a16g128/real_quant_model/model-00036-of-00047.safetensors +3 -0
  39. awq_w4a16g128/real_quant_model/model-00037-of-00047.safetensors +3 -0
  40. awq_w4a16g128/real_quant_model/model-00038-of-00047.safetensors +3 -0
  41. awq_w4a16g128/real_quant_model/model-00039-of-00047.safetensors +3 -0
  42. awq_w4a16g128/real_quant_model/model-00040-of-00047.safetensors +3 -0
  43. awq_w4a16g128/real_quant_model/model-00041-of-00047.safetensors +3 -0
  44. awq_w4a16g128/real_quant_model/model-00042-of-00047.safetensors +3 -0
  45. awq_w4a16g128/real_quant_model/model-00043-of-00047.safetensors +3 -0
  46. awq_w4a16g128/real_quant_model/model-00044-of-00047.safetensors +3 -0
  47. awq_w4a16g128/real_quant_model/model-00045-of-00047.safetensors +3 -0
  48. awq_w4a16g128/real_quant_model/model-00046-of-00047.safetensors +3 -0
  49. awq_w4a16g128/real_quant_model/model-00047-of-00047.safetensors +3 -0
  50. awq_w4a16g128/real_quant_model/model.safetensors.index.json +0 -0
awq_w4a16g128/real_quant_model/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/gushiqiao/nvme/gushiqiao/llama3.1-instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "hidden_act": "silu",
15
+ "hidden_size": 16384,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 53248,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 128,
22
+ "num_hidden_layers": 126,
23
+ "num_key_value_heads": 16,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.43.3",
37
+ "use_cache": false,
38
+ "vocab_size": 128256
39
+ }
awq_w4a16g128/real_quant_model/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.43.3"
12
+ }
awq_w4a16g128/real_quant_model/model-00001-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6116e7d18537341dda2279c5f1566ebd09fe97efcac48c976765866168b682a
3
+ size 4969727800
awq_w4a16g128/real_quant_model/model-00002-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43e972c4d4fdff80b309c55e36180f9577cb5562218ee0a0381cd0a69522ff1
3
+ size 4567539096
awq_w4a16g128/real_quant_model/model-00003-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9390557523625da28262c4c854c7d063c0d6c57eba73617fb300ecad180c0090
3
+ size 4881325456
awq_w4a16g128/real_quant_model/model-00004-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef18ca090c7b79fe5c58966a1047a3b90ab53b6b5fc8ac44f5581cc8a97a767
3
+ size 4985920568
awq_w4a16g128/real_quant_model/model-00005-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd45a8b4906144c67f3ed84411064ff3d492c39a0c78a743d46cd7348e2595b
3
+ size 4881325504
awq_w4a16g128/real_quant_model/model-00006-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79429521ae6ab8cb11497f640c4051d181abd6c8386d00c5391483653fd1d10
3
+ size 4567473392
awq_w4a16g128/real_quant_model/model-00007-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f0644eb7d329ee7c0a5219557a5c2aaa1fffa03389ef2cf8d1fcf45d2a8f5aa
3
+ size 4567539168
awq_w4a16g128/real_quant_model/model-00008-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096c3a1973fa40386caa9e4d53b691e1fd2a3361fb49990ec58fba002afba189
3
+ size 4567539160
awq_w4a16g128/real_quant_model/model-00009-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2239d0efb607dec2a62819af003a2a4a4a514ee0c5b43fed1924224f5a0a371
3
+ size 4881325520
awq_w4a16g128/real_quant_model/model-00010-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a541e2fe636495c4731b7232c504f9eb73d4cc409e6b148fcb62a05d3e3560
3
+ size 4985920632
awq_w4a16g128/real_quant_model/model-00011-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46f2ba66e498d69e6c1f4cb2b0ed8786cbde10066d797f8e5f682736c1fad95
3
+ size 4881325520
awq_w4a16g128/real_quant_model/model-00012-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aaee47402528c6c75adce06308c1e79bf46264bb4a36a5758d4a7ac84635d29
3
+ size 4567473392
awq_w4a16g128/real_quant_model/model-00013-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b23cc74f06380cf833ddbc1ad02e4a9c900ad6703735f824a52b8c053dffa309
3
+ size 4567539168
awq_w4a16g128/real_quant_model/model-00014-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01569c1c7e6d6298963c9d1c6f62706726371cf6528ad5d4381466f128076262
3
+ size 4567539160
awq_w4a16g128/real_quant_model/model-00015-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae81bd6b7aaf239e6b5b4a731b9749d19196dd419fc589353bcf730f657d694
3
+ size 4881325520
awq_w4a16g128/real_quant_model/model-00016-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd1056c16ad689e6fad88c46526e39f4761453019353c34cd890736ba5978f92
3
+ size 4985920632
awq_w4a16g128/real_quant_model/model-00017-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071778b9ab9847fa06c56ccec1dc304f409facb713964a5e095320f397843362
3
+ size 4881325520
awq_w4a16g128/real_quant_model/model-00018-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626d4926b72346cd4e7dcb9771cd8c0c480804f8589c114f1bdbac9e4802fbda
3
+ size 4567473392
awq_w4a16g128/real_quant_model/model-00019-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524c99a33d56951f88142a68c05f10aaef6820b12e5dcc808681520ef1ff1811
3
+ size 4567539168
awq_w4a16g128/real_quant_model/model-00020-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a65238f872551e8352edeacd2aa49829a1d59e662fc9c43fb07588bd10c9f0a
3
+ size 4567539160
awq_w4a16g128/real_quant_model/model-00021-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0128664e5a1ed20f3834c8712048d9155227fce2066048dba73fbd142671ce0
3
+ size 4881325520
awq_w4a16g128/real_quant_model/model-00022-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e4b0002f0334d2ef52fdeabf735ef2eb9702c4db85b619a9b9ae566ea55877c
3
+ size 4985920632
awq_w4a16g128/real_quant_model/model-00023-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f11ecd0d35335ed3a1c7945e9ecaccf5bfbc51d3a9cf8cea7dc899bf822e99d
3
+ size 4881325520
awq_w4a16g128/real_quant_model/model-00024-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:379ba1c4a511819e61d07d39566749d27173d66693b78b52ed8c38687f61cc21
3
+ size 4567473392
awq_w4a16g128/real_quant_model/model-00025-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed53bb55cda8bde4118b2b9a6d229082a99169ac07c5cc81a5126486c9b9d4ac
3
+ size 4567539168
awq_w4a16g128/real_quant_model/model-00026-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8da185a7431fd51e99db7ad368f07dbb2e9aab74ee7baeff1ad34899ebea9ac
3
+ size 4567539160
awq_w4a16g128/real_quant_model/model-00027-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfbebadc4f76077789c52b2e164eb04ebaae46d6462084c5f7391842c815e8de
3
+ size 4881325520
awq_w4a16g128/real_quant_model/model-00028-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb2f558880c634f448bf2d437f37c0f48276c4755b6cf0e19f062ce8600a963
3
+ size 4985920632
awq_w4a16g128/real_quant_model/model-00029-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075beeebe6804fcac1ff2045b93f4718d6dced8152471773e21f012f8054a36b
3
+ size 4881325520
awq_w4a16g128/real_quant_model/model-00030-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d78c0450cfa03bf2f2dd55d671df4141b55abc3a10131b393d24f3b335625dfa
3
+ size 4567473392
awq_w4a16g128/real_quant_model/model-00031-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1e119634d9f15d32734535bedf0cbfd1e3bf4d88e3053c3fe3dd884c3c6a04
3
+ size 4567539168
awq_w4a16g128/real_quant_model/model-00032-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9f7a83e6a62d966b5baf9d9620553f4191731c1ac4c5f5ccc9c895cb3f1cc9
3
+ size 4567539160
awq_w4a16g128/real_quant_model/model-00033-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:726d8fb969ff95d1f2d3d4df12f3be658725826b0e644150af61c6ba5012517b
3
+ size 4881325520
awq_w4a16g128/real_quant_model/model-00034-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:714713fe805cd7390fabf6e8036e71a4697a5eaffb7466197387c63cdec93d28
3
+ size 4985920632
awq_w4a16g128/real_quant_model/model-00035-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9a95f67d8b71f635e3fa6e72940eb7f97a82a59fb6f79a4dd81a6a5b493d7e
3
+ size 4881325520
awq_w4a16g128/real_quant_model/model-00036-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fee2642bc3268d1dc420477f6702eb6245599df806ca6e1b7f05af7616b6347
3
+ size 4567473392
awq_w4a16g128/real_quant_model/model-00037-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e350196f34692072ddd5ecf6e0270b4aa6962c268303a961916de3501806eb
3
+ size 4567539232
awq_w4a16g128/real_quant_model/model-00038-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc51c3921eae5b1406ec76ce0096932ade8f223db41cfecad944cfbfe3d486e3
3
+ size 4567539232
awq_w4a16g128/real_quant_model/model-00039-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a80da3ba200e7d1bae5e533a22e65eec15b9f410f57677ea97aeffa3ca7182d9
3
+ size 4881325592
awq_w4a16g128/real_quant_model/model-00040-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7d0a416ac0a4107db5c09028d7b14f298d6170e4832baaee57effcda6d295f
3
+ size 4985920696
awq_w4a16g128/real_quant_model/model-00041-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff30e5ab78959333aeea1a94e04f649a3d472a3bb30335267780d5b7736ec690
3
+ size 4881325592
awq_w4a16g128/real_quant_model/model-00042-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d5a647c5f546721c155ed35c7550f7094973910d682d6dee31dcf82300b3a62
3
+ size 4567473456
awq_w4a16g128/real_quant_model/model-00043-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c806a412d4de7343da909af16a2d21b51f9c1ee80e3550965d0613ea77be5e8
3
+ size 4567539232
awq_w4a16g128/real_quant_model/model-00044-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:248a4959975dc5a5110d626334a3cca9bddc75e260802f2d5bf209ee4a8d1a8c
3
+ size 4567539232
awq_w4a16g128/real_quant_model/model-00045-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:895da9cebbe5b84edcd8489b308613d02be40c9fe34d577a6e270dad333c834a
3
+ size 4881325592
awq_w4a16g128/real_quant_model/model-00046-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0652d28a99b03b0d8562dda327224751e4a858773625eadd7a51590b9bcceed9
3
+ size 1499301576
awq_w4a16g128/real_quant_model/model-00047-of-00047.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71b079a02069ebe5a5f4f8135815f136afb1d6fc4423620dcb2a14fa399cdf12
3
+ size 4202692736
awq_w4a16g128/real_quant_model/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff