Hugging Face's logo

mlc-ai
/
Llama-3.1-70B-Instruct-fp8-MLC

MLC-LLM
Model card Files Community
ruihanglai commited on
Commit
f3efba8
•
1 Parent(s): 6c9e7d5

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_131.bin +3 -0
  42. params_shard_132.bin +3 -0
  43. params_shard_133.bin +3 -0
  44. params_shard_134.bin +3 -0
  45. params_shard_135.bin +3 -0
  46. params_shard_136.bin +3 -0
  47. params_shard_137.bin +3 -0
  48. params_shard_138.bin +3 -0
  49. params_shard_139.bin +3 -0
  50. params_shard_14.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": 8192,
7
+ "intermediate_size": 28672,
8
+ "num_attention_heads": 64,
9
+ "num_hidden_layers": 80,
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:dc2dabfaed3a831eeb7b232e8853e3af89b1132e36d24d79c66270c332e62a07
3
+ size 2101346304
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ffb3f2735de9b562c99f4b71ccee7ce2dda72ee0e403bc5a23de6cb690185d5
3
+ size 2101346304
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c8ce5c8e549123f42afd18e20d5911d11c86dd08d3b33490475cbb5b05b611
3
+ size 234881024
params_shard_100.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff1dbc1df588f0bd0f4d052ddc00130d23d8c1e248be62e28afdb93dfd7febb9
3
+ size 234881024
params_shard_101.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f82fbfdfa4851542964f8fc7c4c9b89c6c7c822b5792700f21dc5fdf6c4c91
3
+ size 469762048
params_shard_102.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218389b7335876ab9978e75c4bc36912f2eeb9fe418c09cba8007453ea8103e6
3
+ size 83886080
params_shard_103.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157aaa1b18d65677468a47f199b1d43bc48d4721bfebc355ac26293a6a0b73e3
3
+ size 67108864
params_shard_104.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b398c59fcef80358486665da4f52a9f67198454408878ab5b5ac1c859372e7
3
+ size 234881024
params_shard_105.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25985a6251f2d114e22c56972f2e539fcce2857390180363edac62e44b22d50
3
+ size 469762048
params_shard_106.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d81ef1efc4b0bb869bacf6ff4c819fe9e8071702e620d995b05d3755ad378578
3
+ size 83886080
params_shard_107.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:040cf56c6df33d2f2c14b4abff670daf8a6a15b8b8ba6ed164e1735f97b51d59
3
+ size 67108864
params_shard_108.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7249c11146c4b5c3e840711682cb31ce70d1d4c669d125b83f92ea83cdbe561
3
+ size 83886080
params_shard_109.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c2833b2085441c489d1b4f2635514864748f914462db7e8d026bb186047d126
3
+ size 67108864
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7ca5f485679c010000912727180717ffcb4f51d0607fa31e855dbc183dc41b2
3
+ size 469762048
params_shard_110.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e118a796930ed18d3f5a5c9ca3ed2077e2d7d06f1a9a965797e16231c8109e0
3
+ size 234881024
params_shard_111.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af71c0a9357f81d02a4a5216591be8b992737b526571c19595585b2301b9231
3
+ size 469762048
params_shard_112.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6f0c78d97febb8c98131f5ebe0e36a2a3378edfbcc398a387cdeb6ca38d8b3
3
+ size 234881024
params_shard_113.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:589ad6dd194ac22bee140d90a28772ef9e72405a93f4602eea4b88a96bfc8d37
3
+ size 469762048
params_shard_114.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e7deda65ec7cc187b49204e9bff6066832144425f743ff300663fefccf873a4
3
+ size 83886080
params_shard_115.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d456cd6bce45373f7e47702017b0c16d7384f4d12a1d0326a14b40853797191e
3
+ size 67108864
params_shard_116.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bffbd31bb07682dcef536da8cab7eb05b338648c6f11b2f75dc6bea798106ca3
3
+ size 234881024
params_shard_117.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aede0d61f7023daa2bed3032f99d9d44b2e1996efb00eb2d7defb528c385d00a
3
+ size 469762048
params_shard_118.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e59042511f4f335ed61fd73072e0ae448d136d21f90cd5ff57d010e07806b9
3
+ size 83886080
params_shard_119.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0d9b8d1fb05b0a7e01c8b51ad7db2623df99e10e43f06d1ba0d73bbb2aa9a0
3
+ size 67108864
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f5e10d7f6e4570b1fd7c92defe86d69fd9a2b49100f841e069cc2a39a9e211
3
+ size 83886080
params_shard_120.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec7d22082ae111a6248c07100cbc04e85f070691de6c31a7234369d12a4b976e
3
+ size 83886080
params_shard_121.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f159453f16d21cba13d8705619de2aa17a871f9d95d698be99fbb15f218a93f
3
+ size 234881024
params_shard_122.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:954f9e48c7a76d0dc49cf42d6a54c5aa2d2b9f5fab295178c098239351fff7ae
3
+ size 469762048
params_shard_123.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b1b0b76ea31d4e4fd62e34bdc02ee926b9fa9c4a29da4e721c6e48fbd69e1e
3
+ size 67108864
params_shard_124.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af9fb36885f568fcccbb6989a7f9f2f73482950151d5f1ea095c8c180219c03
3
+ size 234881024
params_shard_125.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b1765e00ea5812328bd887d7ff2fda19c9457107e650c455656119d7eeb5db9
3
+ size 469762048
params_shard_126.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7918460a1425d7587ef1314f1e6b6540733bed476def453086500ecc36fb701
3
+ size 83886080
params_shard_127.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d3ee7c85c7b63c432193541a45807043810be69fb8c9b18421871b94fead9c2
3
+ size 67108864
params_shard_128.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d9ab3d03a4a9d112981a59fa08642fc08df4e94e753a8853c57a31e84a5e02
3
+ size 234881024
params_shard_129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c5db62f6a5fc4e8382d72a0b18769f8321a032cc9ada5a4f256f3d56db4fae
3
+ size 469762048
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257a27bc7e5adabd7faea7bfa329eaadec9d488ce1e273f57a3d4c016b36b2af
3
+ size 67108864
params_shard_130.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe99cc57cd1a2445769d0ac8609e2ce54148ca9db7a44bdf58d4d82997c027c
3
+ size 83886080
params_shard_131.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96e532457772132ac83ebe481b0d761ca77184233cead27aec97d120e4ae68b7
3
+ size 67108864
params_shard_132.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44c636d8d0ed5f1c57e6a203368499462d0b914c455e85968a1831eb09bee426
3
+ size 234881024
params_shard_133.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33cb8103fa6c46b3ccc9372afab886716908f894e51e978d339b873d9e909f21
3
+ size 469762048
params_shard_134.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc6af934cf66aaa3622b725bfb63e03608283543577db5a3baab90b25d11c5b
3
+ size 83886080
params_shard_135.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b08b2f0be1523ff288263ed8555d4ef4a04aaf67078b504f9a41e6e9d542e97
3
+ size 67108864
params_shard_136.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b7a06c680c721e48260bd248b111840383bce308ba3ee44547913853169a9f
3
+ size 234881024
params_shard_137.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2cc438c32e3077a679111e30b60b88952c054f66a6d3ce34caf6050c3829a00
3
+ size 469762048
params_shard_138.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7203892139e9a4ae2b7835f3c5bc534c63f32aab40351beaf74ac7a3a69c65d2
3
+ size 83886080
params_shard_139.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d81b77dbc57dc556e3b416386afbb62a2d455f39f2a1c89d60a6e4d968397fa
3
+ size 67108864
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d02e648740c9644ed13e6ed8a46aa9289ce4cd5b2326c300ae058493f0f8933
3
+ size 234881024