Hugging Face's logo

relaxml
/
Llama-3.1-405B-Instruct-QTIP-3Bit-TP8

Safetensors
llama
Model card Files Community
2

Upload folder using huggingface_hub

#2
by at676 - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+5720
-0
Files changed (37) hide show
  1. config.json +52 -0
  2. generation_config.json +12 -0
  3. model-00001-of-00034.safetensors +3 -0
  4. model-00002-of-00034.safetensors +3 -0
  5. model-00003-of-00034.safetensors +3 -0
  6. model-00004-of-00034.safetensors +3 -0
  7. model-00005-of-00034.safetensors +3 -0
  8. model-00006-of-00034.safetensors +3 -0
  9. model-00007-of-00034.safetensors +3 -0
  10. model-00008-of-00034.safetensors +3 -0
  11. model-00009-of-00034.safetensors +3 -0
  12. model-00010-of-00034.safetensors +3 -0
  13. model-00011-of-00034.safetensors +3 -0
  14. model-00012-of-00034.safetensors +3 -0
  15. model-00013-of-00034.safetensors +3 -0
  16. model-00014-of-00034.safetensors +3 -0
  17. model-00015-of-00034.safetensors +3 -0
  18. model-00016-of-00034.safetensors +3 -0
  19. model-00017-of-00034.safetensors +3 -0
  20. model-00018-of-00034.safetensors +3 -0
  21. model-00019-of-00034.safetensors +3 -0
  22. model-00020-of-00034.safetensors +3 -0
  23. model-00021-of-00034.safetensors +3 -0
  24. model-00022-of-00034.safetensors +3 -0
  25. model-00023-of-00034.safetensors +3 -0
  26. model-00024-of-00034.safetensors +3 -0
  27. model-00025-of-00034.safetensors +3 -0
  28. model-00026-of-00034.safetensors +3 -0
  29. model-00027-of-00034.safetensors +3 -0
  30. model-00028-of-00034.safetensors +3 -0
  31. model-00029-of-00034.safetensors +3 -0
  32. model-00030-of-00034.safetensors +3 -0
  33. model-00031-of-00034.safetensors +3 -0
  34. model-00032-of-00034.safetensors +3 -0
  35. model-00033-of-00034.safetensors +3 -0
  36. model-00034-of-00034.safetensors +3 -0
  37. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 3,
28
+ "L": 16,
29
+ "V": 2,
30
+ "codebook": "bitshift",
31
+ "codebook_version": 0,
32
+ "decode_mode": "quantlut_sym",
33
+ "split_for_tp": true,
34
+ "td_x": 16,
35
+ "td_y": 16,
36
+ "tlut_bits": 9
37
+ },
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": {
40
+ "factor": 8.0,
41
+ "high_freq_factor": 4.0,
42
+ "low_freq_factor": 1.0,
43
+ "original_max_position_embeddings": 8192,
44
+ "rope_type": "llama3"
45
+ },
46
+ "rope_theta": 500000.0,
47
+ "tie_word_embeddings": false,
48
+ "torch_dtype": "bfloat16",
49
+ "transformers_version": "4.45.2",
50
+ "use_cache": true,
51
+ "vocab_size": 128256
52
+ }
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-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c917dcdc276eb70bef2a46721a83091ab551eeb291e99d340eeffecf50991f
3
+ size 4744289776
model-00002-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb1c945146f52f2a15f92fffbd6f90bf32b59e26a9a638e7af3362e40a0226b
3
+ size 4785579736
model-00003-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a61ea38e7fa7c3314e6f33e9cd2220cb080d74f83aa0f4b811d4672d7945e2
3
+ size 4785579736
model-00004-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e9b96bf2f7cdb3bf51d2f7337dd411afcf8a5b599dc48b4a7485acf0854d493
3
+ size 4785579856
model-00005-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31626c1a285a6dcea890f28e9478b58553366b6cf1480be2f43a8780721f6f9d
3
+ size 4785579912
model-00006-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3211aeaa1d51cfc2973d1f574f9b2126f7fd3b4bab1f6ed353193fa855483775
3
+ size 4785579912
model-00007-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e2978ad58ecad35f0ab5ae2c39fa927af193ff9b310ef681fa41cf98a62aa3
3
+ size 4785579912
model-00008-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87cc6f4c7aaa6e8a491c963447d6f4c545340bb09535b1fbcb547cfd6b54433f
3
+ size 4785579912
model-00009-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f703f14dd352af3a2f7a8c0c92150c8b93b9226d0ed2267f223c69ca2bd1ff5
3
+ size 4785579912
model-00010-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998c305d6a53f753f28233f18124c28466c73549f795a72c85ee5c85939739cf
3
+ size 4785579912
model-00011-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f503cb69f9f615284bb794df883348c5252c03d87a1a588459bb411e215345b
3
+ size 4785579912
model-00012-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c73b2a88e4ebabcc9a29f61226b88e677b9f6bbe5f8360d7243efc350b56c49
3
+ size 4785579912
model-00013-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee7ff77231860d33d1542655234ef5240dfb4f7a1cdf54a61a97b633db6e801
3
+ size 4785579912
model-00014-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703eee83cf6e33e31db9ef2b1d55348b0e0b944d565b8fd0ac7f859242b5db8a
3
+ size 4785579912
model-00015-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8dc51f9c90d9fc69e450ac038f0763428b74bf2366d046e751282e11728e5c
3
+ size 4785579912
model-00016-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4775acc45a96a543dc546c301dab8bce0743e89f4d19a2a0cb05306711ee2a7c
3
+ size 4785579912
model-00017-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e111583abfabd070838b602353e0508182b411a29bd48654fa9597db4065ce
3
+ size 4785579912
model-00018-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1310b13685ea71f4f1a44818320d874bae5a0871bf569f3c2e1d9e4fe3907040
3
+ size 4785579912
model-00019-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72abe511a4033935b7f0587143ff2dba6517aadcdb37e4ff4bb689fcda0c228a
3
+ size 4785579912
model-00020-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa823cf5a40880bcbeba39b8ff37d62354bf4df77629a65ed15e6f25a29f9b04
3
+ size 4785579912
model-00021-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab52dab01cbb0ec1398698248eedc70b1f2278d2942ee3806a08c990d03a241a
3
+ size 4785579912
model-00022-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06418c6c667ca4445ecb4cf0da244b368e2b38556929a0d7dd9e7c569c00a5f6
3
+ size 4785579912
model-00023-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3fa229890d1788ebd3668c967d08e9db7038f6f77e88dc1f17a5b72e6451ec8
3
+ size 4785579912
model-00024-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e24c1841c1197c86117b8caf5c0544bb4b59234331efb0e568ea6ef3bac24aa
3
+ size 4785579912
model-00025-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17bb9c81382b39a1bdda7e37f3147691f5480f757b1d68483a2842518d84d629
3
+ size 4785579912
model-00026-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3904590a62f7b31969d940aa5de38a35f0c2e8573a9983bcf46d487ade5a597
3
+ size 4785579936
model-00027-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c65d60592f907f6afc6c1cb2a762e1f6f7b678e2a728bfef53dee0028e994e2
3
+ size 4785580088
model-00028-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e530a4ae5bfb460c3bdff294c35da19bb7f4e39ffd34937e536565b3b7ebc4c
3
+ size 4785580088
model-00029-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace55e9768cafa03a400beefcda03ff661088d8fa8e68004eb30660389214ff8
3
+ size 4785580088
model-00030-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:919f8be272b4625ad871ef6f2698bf4fc19229a50ffe3d10f39f0eef3503d5ec
3
+ size 4785580088
model-00031-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3691afc5db7eb1489d5561593953ae1959504b2e7f92cde9bef817d1f7af30f
3
+ size 4785580088
model-00032-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f1b2df01c3638054194742dfc4cecdf58049afa72b84a00d0e65d3023239e65
3
+ size 4785580088
model-00033-of-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e52c41500676ca8a00a1910e6341bbdcadb6eb15fc5fc36adb653758d2b0e4
3
+ size 1851225824
model-00034-of-00034.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