Hugging Face's logo

mlc-ai
/
Llama-3.1-8B-Instruct-fp8-MLC

MLC-LLM
Model card Files Community
ruihanglai commited on
Commit
5177197
•
1 Parent(s): 9334449

initial commit

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. mlc-chat-config.json +90 -0
  2. ndarray-cache-b16.json +0 -0
  3. ndarray-cache.json +0 -0
  4. params_shard_0.bin +3 -0
  5. params_shard_1.bin +3 -0
  6. params_shard_10.bin +3 -0
  7. params_shard_100.bin +3 -0
  8. params_shard_101.bin +3 -0
  9. params_shard_102.bin +3 -0
  10. params_shard_103.bin +3 -0
  11. params_shard_104.bin +3 -0
  12. params_shard_105.bin +3 -0
  13. params_shard_106.bin +3 -0
  14. params_shard_107.bin +3 -0
  15. params_shard_108.bin +3 -0
  16. params_shard_109.bin +3 -0
  17. params_shard_11.bin +3 -0
  18. params_shard_110.bin +3 -0
  19. params_shard_111.bin +3 -0
  20. params_shard_112.bin +3 -0
  21. params_shard_113.bin +3 -0
  22. params_shard_114.bin +3 -0
  23. params_shard_115.bin +3 -0
  24. params_shard_116.bin +3 -0
  25. params_shard_117.bin +3 -0
  26. params_shard_118.bin +3 -0
  27. params_shard_119.bin +3 -0
  28. params_shard_12.bin +3 -0
  29. params_shard_120.bin +3 -0
  30. params_shard_121.bin +3 -0
  31. params_shard_122.bin +3 -0
  32. params_shard_123.bin +3 -0
  33. params_shard_124.bin +3 -0
  34. params_shard_125.bin +3 -0
  35. params_shard_126.bin +3 -0
  36. params_shard_127.bin +3 -0
  37. params_shard_128.bin +3 -0
  38. params_shard_129.bin +3 -0
  39. params_shard_13.bin +3 -0
  40. params_shard_130.bin +3 -0
  41. params_shard_14.bin +3 -0
  42. params_shard_15.bin +3 -0
  43. params_shard_16.bin +3 -0
  44. params_shard_17.bin +3 -0
  45. params_shard_18.bin +3 -0
  46. params_shard_19.bin +3 -0
  47. params_shard_2.bin +3 -0
  48. params_shard_20.bin +3 -0
  49. params_shard_21.bin +3 -0
  50. params_shard_22.bin +3 -0
mlc-chat-config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "llama",
4
+ "quantization": "e4m3_e4m3_f16",
5
+ "model_config": {
6
+ "hidden_size": 4096,
7
+ "intermediate_size": 14336,
8
+ "num_attention_heads": 32,
9
+ "num_hidden_layers": 32,
10
+ "rms_norm_eps": 1e-05,
11
+ "vocab_size": 128256,
12
+ "tie_word_embeddings": false,
13
+ "position_embedding_base": 500000.0,
14
+ "rope_scaling": {
15
+ "factor": 8.0,
16
+ "low_freq_factor": 1.0,
17
+ "high_freq_factor": 4.0,
18
+ "original_max_position_embeddings": 8192,
19
+ "rope_type": "llama3"
20
+ },
21
+ "context_window_size": 131072,
22
+ "prefill_chunk_size": 8192,
23
+ "num_key_value_heads": 8,
24
+ "head_dim": 128,
25
+ "tensor_parallel_shards": 1,
26
+ "pipeline_parallel_stages": 1,
27
+ "max_batch_size": 128
28
+ },
29
+ "vocab_size": 128256,
30
+ "context_window_size": 131072,
31
+ "sliding_window_size": -1,
32
+ "prefill_chunk_size": 8192,
33
+ "attention_sink_size": -1,
34
+ "tensor_parallel_shards": 1,
35
+ "pipeline_parallel_stages": 1,
36
+ "temperature": 0.6,
37
+ "presence_penalty": 0.0,
38
+ "frequency_penalty": 0.0,
39
+ "repetition_penalty": 1.0,
40
+ "top_p": 0.9,
41
+ "tokenizer_files": [
42
+ "tokenizer.json",
43
+ "tokenizer_config.json"
44
+ ],
45
+ "tokenizer_info": {
46
+ "token_postproc_method": "byte_level",
47
+ "prepend_space_in_encode": false,
48
+ "strip_space_in_decode": false
49
+ },
50
+ "conv_template": {
51
+ "name": "llama-3_1",
52
+ "system_template": "<|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|>",
53
+ "system_message": "You are a helpful, respectful and honest assistant.",
54
+ "system_prefix_token_ids": [
55
+ 128000
56
+ ],
57
+ "add_role_after_system_message": true,
58
+ "roles": {
59
+ "user": "<|start_header_id|>user",
60
+ "assistant": "<|start_header_id|>assistant",
61
+ "tool": "<|start_header_id|>ipython"
62
+ },
63
+ "role_templates": {
64
+ "user": "{user_message}",
65
+ "assistant": "{assistant_message}",
66
+ "tool": "{tool_message}"
67
+ },
68
+ "messages": [],
69
+ "seps": [
70
+ "<|eot_id|>"
71
+ ],
72
+ "role_content_sep": "<|end_header_id|>\n\n",
73
+ "role_empty_sep": "<|end_header_id|>\n\n",
74
+ "stop_str": [],
75
+ "stop_token_ids": [
76
+ 128001,
77
+ 128008,
78
+ 128009
79
+ ],
80
+ "function_string": "",
81
+ "use_function_calling": false
82
+ },
83
+ "pad_token_id": 0,
84
+ "bos_token_id": 128000,
85
+ "eos_token_id": [
86
+ 128001,
87
+ 128008,
88
+ 128009
89
+ ]
90
+ }
ndarray-cache-b16.json ADDED
The diff for this file is too large to render. See raw diff
 
ndarray-cache.json ADDED
The diff for this file is too large to render. See raw diff
 
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e298f11a83e4e692eca63ac98c00d32160dfc1685cf2c66e80afe0838db316c5
3
+ size 1050673152
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc122e0fb6f83c07b71aabce2de461e54f9f0aed2250e85afa9c1db0b5a83771
3
+ size 58720256
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8942f0cc70719ec29e1abd1778bdd8c9e201d8610ce8d688c3e6797c83afaf
3
+ size 58720256
params_shard_100.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3fe6029d2758104b3379d12390878503a289569c7832c3ef460975cd11a5e0
3
+ size 25165824
params_shard_101.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6687fcd2e0b486769293e0053c80c09d70acb297c6042513e91c9a72ad7ee90b
3
+ size 16777216
params_shard_102.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb2e4ef61fa413a68a13dc63ea4a46b5885b4487b6cd082a4a65e00792d11e4
3
+ size 58720256
params_shard_103.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4bb810b4d3f0e2c5ff0cfbb1da40d45e072ae329478489499e231ad40782a9d
3
+ size 117440512
params_shard_104.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c433cafb83b20af0ed73333ab484f7683ac40a719f6eafc91ee18cc2006fb9a
3
+ size 25165824
params_shard_105.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dd4056302099d16f93704e5b858ddfc9370c150dfcf83ee68f895be2e250a16
3
+ size 16777216
params_shard_106.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9b788fb90d5d1856deabcc81fbaf4dc596b889a9e9b87253ce8ea293be2db3
3
+ size 58720256
params_shard_107.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfdd6d1ab6f2d2d61bb809da6a856c368579925a73efad087e8a2ca4ec9f20ac
3
+ size 117440512
params_shard_108.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d955400c5cee5b76bb6a8e27559adb0e45cf050c6873e06d8d488ebbfb27bce
3
+ size 25165824
params_shard_109.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e944302780f435161bc9d9bd9b8eca9108fe2e9e79f108e4d35b5b6cc91743d8
3
+ size 16777216
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09dec38b681c2ae2e577aba8abf07d70a8a785ab7d57ee83d9d3230fffc4e62d
3
+ size 117440512
params_shard_110.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3960cbd71760e016a9d97d9d7819d94776e9c3fd23ebf3b340bafbd9c843bc8
3
+ size 58720256
params_shard_111.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd4fd981190c79f6f23f5a24f029a5a9c92990bc5562b60f7eeecb57961e5a4
3
+ size 117440512
params_shard_112.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f275ac3816f7dbc9f856a545e2e2f66e1bc394db0447f76b26710e733c9e57
3
+ size 25165824
params_shard_113.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e0200f7506ab544faf00c13d92a21f504a03f44a0f9884699b40566a989e35
3
+ size 16777216
params_shard_114.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d0b62f57276f8111f8666dbb23dd94badf47213ae7fcd992459508ce7ee8d75
3
+ size 58720256
params_shard_115.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68ad6739466f1919aef12b3d5fd9ccedb0112b938d7027a4e7c3e92a21cf8b79
3
+ size 117440512
params_shard_116.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f394d69feccdfbacaecc8f325d74bac348f587d8cced34324443f61b251a4157
3
+ size 25165824
params_shard_117.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb71295e9a119b9a55297456217003d00684e0243569b08518b5f58acac83aa5
3
+ size 16777216
params_shard_118.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb0f6ba389bd83d3e6bef516bd0439769c85de643f7ed8214b1a81e0b868c02
3
+ size 58720256
params_shard_119.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d2a5433d71ea287718d3e96f013bae8458c72c119e0c433b1dde16041f3539
3
+ size 117440512
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff52ffa9a5fcbc93317ab05d538063d127ccdc48a6916f5fc440eee766ff94fc
3
+ size 25165824
params_shard_120.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29da8ea8b1134ce8207e01ad9b292586c54c0ef0deb3428781c9279b3deac6e
3
+ size 25165824
params_shard_121.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700bc5ad92d0793805030ca853e7ffebcfaeb3b60961e06121e1c7def630937f
3
+ size 16777216
params_shard_122.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd0c86f2baf1d6a9400270b4e59376b86a59f98d831f7ed6de02b7894118d21
3
+ size 58720256
params_shard_123.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a47d6ca13f369dcb8eecf05dd2757c6d8861e44676d1b766147eb0dd43fc346f
3
+ size 117440512
params_shard_124.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076fde76c6cbb78edc1a865be63ff1bf3be255866feaff0e3380a8f6e782df02
3
+ size 25165824
params_shard_125.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b20c46e2079113417c1a730a5b52d20128873bddfe9e4dd4bf3e714ae778e653
3
+ size 16777216
params_shard_126.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6b4caf002641811aa5a2d4f76b8327e3ab536a0db148abac4c710bda20d49d
3
+ size 117440512
params_shard_127.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428822cf4f209ec8e47dadcad2ea0e47e1d309e4e67273f5551b3064dc6b0026
3
+ size 25165824
params_shard_128.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1457676eaf556d0371c9c95cdc2f60db1c45aaf8d86c7976ca2dfa0cbc3ab415
3
+ size 16777216
params_shard_129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043ea9526b535f06a9bc3ce667d3372af98587f57344689f90bb718c3959cf45
3
+ size 25698560
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43b7fbc0a92ab01544b5b8dee581c82876a0b1146cad28c4ae986f64a3ed32f
3
+ size 16777216
params_shard_130.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3d2a7950b404d3223ac4096731e9d91d95250e045a1fc9e060493aba0654e16
3
+ size 256
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c847a736686c830d6348db5cbb0a048d249463bf97e661f61607d79f1526c57
3
+ size 58720256
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b07305bf4bc7bd6ab021d351db743f5d9558ce0a68c3813c7f72783a2ad02b63
3
+ size 117440512
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1432df6dfc7863f098b99f7a797488e85a8c62631b8d1fa662289fc568d3a7
3
+ size 25165824
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87f8de9ba42d4751d4fcfe486b58a6e279ee7215e241869f0fdd019b00b338ec
3
+ size 16777216
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a98777934eb0b69fea8b497cfa82d22e7275c0556bfb70ca7a77bca1d1b042c
3
+ size 58720256
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620065cc892bbc0a33e7d0bd4a430db422d1c7273e5cb03f8f7bbf9f85d13861
3
+ size 117440512
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e979c418bb40e497b73c6ad34d90be9a44c9f5373336cf49249c33f550f4036f
3
+ size 1050673152
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:092d67889686a0c2ad86f7c84de0b0324e45e5348d53bf93ecbbcdd6b846551f
3
+ size 25165824
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76fedf29a21077cfbf370e1704b9749f346d13b17c01d62e53149fdc70c95ce0
3
+ size 16777216
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766fac88f8cdd7d9d0551c3674ba17400b9720f4741597423635593bee82bf4f
3
+ size 58720256