Hugging Face's logo

relaxml
/
Llama-3.1-405B-Instruct-QTIP-2Bit

Safetensors
llama
Model card Files Community
1

Upload folder using huggingface_hub

#1
by at676 - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+3922
-0
Files changed (26) hide show
  1. config.json +51 -0
  2. generation_config.json +12 -0
  3. model-00001-of-00023.safetensors +3 -0
  4. model-00002-of-00023.safetensors +3 -0
  5. model-00003-of-00023.safetensors +3 -0
  6. model-00004-of-00023.safetensors +3 -0
  7. model-00005-of-00023.safetensors +3 -0
  8. model-00006-of-00023.safetensors +3 -0
  9. model-00007-of-00023.safetensors +3 -0
  10. model-00008-of-00023.safetensors +3 -0
  11. model-00009-of-00023.safetensors +3 -0
  12. model-00010-of-00023.safetensors +3 -0
  13. model-00011-of-00023.safetensors +3 -0
  14. model-00012-of-00023.safetensors +3 -0
  15. model-00013-of-00023.safetensors +3 -0
  16. model-00014-of-00023.safetensors +3 -0
  17. model-00015-of-00023.safetensors +3 -0
  18. model-00016-of-00023.safetensors +3 -0
  19. model-00017-of-00023.safetensors +3 -0
  20. model-00018-of-00023.safetensors +3 -0
  21. model-00019-of-00023.safetensors +3 -0
  22. model-00020-of-00023.safetensors +3 -0
  23. model-00021-of-00023.safetensors +3 -0
  24. model-00022-of-00023.safetensors +3 -0
  25. model-00023-of-00023.safetensors +3 -0
  26. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-405B-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
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 16384,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 53248,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 128,
23
+ "num_hidden_layers": 126,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "quip_params": {
27
+ "K": 2,
28
+ "L": 16,
29
+ "V": 2,
30
+ "codebook": "bitshift",
31
+ "codebook_version": 0,
32
+ "decode_mode": "quantlut_sym",
33
+ "td_x": 16,
34
+ "td_y": 16,
35
+ "tlut_bits": 9
36
+ },
37
+ "rms_norm_eps": 1e-05,
38
+ "rope_scaling": {
39
+ "factor": 8.0,
40
+ "high_freq_factor": 4.0,
41
+ "low_freq_factor": 1.0,
42
+ "original_max_position_embeddings": 8192,
43
+ "rope_type": "llama3"
44
+ },
45
+ "rope_theta": 500000.0,
46
+ "tie_word_embeddings": false,
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.45.2",
49
+ "use_cache": true,
50
+ "vocab_size": 128256
51
+ }
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": "4.45.2"
12
+ }
model-00001-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04d2984f2da1a7c01c0595613b447817dcd344988b2cd6ac0f57d6126327aa4f
3
+ size 4782285584
model-00002-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d51f0c2199bc5cf23697db0a238648cef87d6d17c8b34df1cff6b33b3d2b88dd
3
+ size 4787608080
model-00003-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a25ecdac67741797eee196b011abe7709ff4bf79777c543dced29f510bd7b2
3
+ size 4787608168
model-00004-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96398cdec1da75e421dcfe46fdc3d0c087b73e6d9a8571ec9a3a04385019f107
3
+ size 4787608264
model-00005-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0ee5db899ba3624ba016cb2f9c82bffc79e60904157887bbd2fc2f7316d682
3
+ size 4787608264
model-00006-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2503f55df6d5423acbc71fa68c75e02cfc11acbdc59209d87fb2d9c54e51098
3
+ size 4787608264
model-00007-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eefd91645f0568f1402ebaaaf7201d69c74228a945e81f6f8fbdc268a835ccec
3
+ size 4787608264
model-00008-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e121b7ffcba1c643a7732be1b96f949998110ad331d897aff90abe13dca1f512
3
+ size 4787608264
model-00009-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfbb0a5bfd7bcdcceeb5309f5f48124855ca2d5c19bb61cd3e8cd0eaf0e56ef9
3
+ size 4787608264
model-00010-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1419ec19a8f3b655f5c6cd0360469cffce28170ce349fc70ece55564600f02fd
3
+ size 4787608264
model-00011-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b742883f04ec0e41c7cd66a80279afd4469b55f8836e629d8b07764bffed1a
3
+ size 4787608264
model-00012-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456ae5d512826235cb7d3a062afedc6e28c6855aa446b49c4e6361189692d738
3
+ size 4787608264
model-00013-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca63f479ea15b39535657fc8b2bc066e5fb1b79c01b19a80aabd8b146e252d71
3
+ size 4787608264
model-00014-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c89464f248a54d52ffcce955ba39633cdca357181de938e1efe896ece9161306
3
+ size 4787608264
model-00015-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44be9e9633e2d56c3f8c7b6ef175b02db7f744fe600900bd23b9d979cd38c904
3
+ size 4787608264
model-00016-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8603ae05a449d5ffc10cd23612f1b65faf9f213a3aec960050f4ef2862644ec4
3
+ size 4787608264
model-00017-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e13ff34432b74effc7dade394f7d9e7ecf0130a7bdfe4a3a453bd2fb92ecb0b2
3
+ size 4787608264
model-00018-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f62f217e5eb9be257c394998c3d78c49f4d2daba10a3e657a2a5a47dd4e5b85
3
+ size 4787608344
model-00019-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10e4129eda4f782a7d90675420ab83e38e5db872061581a869775f1481ecb68e
3
+ size 4787608440
model-00020-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b2862a305cdb846160545e2524d0bbf5937e986a450ab37c1874a267349ccc9
3
+ size 4787608440
model-00021-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b661d5d847b890b6bf6593e0b8aad3e228aacde9ad886da48353509dc3494a7
3
+ size 4787608440
model-00022-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0095d467f0be13a4934165c27ecc39fb0fe37aa2e1ee267b3e4ffa7d77c4a61
3
+ size 4208048472
model-00023-of-00023.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