Hugging Face's logo

relaxml
/
Llama-3.1-405B-Instruct-QTIP-2Bit-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
+5687
-0
Files changed (26) hide show
  1. config.json +52 -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 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2,
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-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ecc4b88297075b087cffc38786bd865496e8d94280ba52f771900e44c59be3
3
+ size 4782286936
model-00002-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1e23c3cea3d9dffc29f5bd83b43f1d64745bd7d0a7589ac5ecb46293a609b8d
3
+ size 4787616320
model-00003-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4b130b89d32aeaa5e3014f1a73da3728ba52ae72c8ff04e13ab3be7ae4861e1
3
+ size 4787616448
model-00004-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdc3fde66f211aa2696a856bfe45fc64ed9e5b755a5b7b6ecf327167cae27f7b
3
+ size 4787616584
model-00005-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59be449a6df2c10e8c4a606fc742f4280a965351241d11bf63b36b3cc1dc1d2d
3
+ size 4787616584
model-00006-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c65bffe8e7612964a601ed81d9031dad29436a2ab110446639d6ce84bda9478
3
+ size 4787616584
model-00007-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:955d38bf18ad91391302301af89a7b4b870c49223d327f1497a44d43bb1d8c21
3
+ size 4787616584
model-00008-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:954a7d1458d4f5d66777bd41ee6470dbda22cbce8f383a0c4650b72cf2a6b12a
3
+ size 4787616584
model-00009-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c244c4c6a3c5c25d3f562dc1df3423f034f60ac3e9992253539c8fce6d907de8
3
+ size 4787616584
model-00010-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8d60bbf9a7292d3f32d73a060ce3f59220b5d5f198caa8e89c4736754636b18
3
+ size 4787616584
model-00011-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a9a46c00166ed544028e467f22cf16c86110152234efcdb994074a82e4a012
3
+ size 4787616584
model-00012-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c53065e01f6bdd73778908cfd23104dffaa1d80d9d25611719ff8fbc59fa2ca5
3
+ size 4787616584
model-00013-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5bdb09db82110947c98d0542351d0c7f8353e9148e320e6ba60945824c388c1
3
+ size 4787616584
model-00014-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ccdcc1b6c554b508c4866b215493a0cf24d6ef280300f756eea705b5ffef69
3
+ size 4787616584
model-00015-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df284aa2cccc6b849bd36579e4fa660d7f469ec9a998540ad11ac903dbd71ac6
3
+ size 4787616584
model-00016-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46674e6a54ccecb95486d16dbcc1d1691227065be8c7108decba294c7cd3dd3
3
+ size 4787616584
model-00017-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d6f5871cc5e09b3997a59abb33b284417c0434e407aa3ca2dc6d24a7c406fcb
3
+ size 4787616584
model-00018-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa2703cf4f297896c8ee1cdb2ca5f9ab6c2417d3a3f7e246cd9117efd7262c0
3
+ size 4787616712
model-00019-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa5403b9a1163578e6cd1293032c481568d66fdb174c0146e04e380caa94aba3
3
+ size 4787616848
model-00020-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3792e6b4ae571c7ff44357a0b5058c2fb636788ae614295e5409e166c99560f7
3
+ size 4787616848
model-00021-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186cd6155bcbe4c2a746317d2a9d646b1c985cc9459a2120270e03cb2838bd17
3
+ size 4787616848
model-00022-of-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c963f5a4fbdfc48b1845aa1dce68bf99d5df3e02a4722220a00b237f91767bd
3
+ size 4208055480
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