Hugging Face's logo

mlc-ai
/
gemma-3-12b-it-q4f32_1-MLC

MLC-LLM
web-llm
Model card Files
xet
Community
riczhou commited on
Commit
af0fe51
·
verified ·
1 Parent(s): 623fa0b

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +3 -0
  3. mlc-chat-config.json +99 -0
  4. ndarray-cache-b16.json +0 -0
  5. ndarray-cache.json +0 -0
  6. params_shard_0.bin +3 -0
  7. params_shard_1.bin +3 -0
  8. params_shard_10.bin +3 -0
  9. params_shard_100.bin +3 -0
  10. params_shard_101.bin +3 -0
  11. params_shard_102.bin +3 -0
  12. params_shard_103.bin +3 -0
  13. params_shard_104.bin +3 -0
  14. params_shard_105.bin +3 -0
  15. params_shard_106.bin +3 -0
  16. params_shard_107.bin +3 -0
  17. params_shard_108.bin +3 -0
  18. params_shard_109.bin +3 -0
  19. params_shard_11.bin +3 -0
  20. params_shard_110.bin +3 -0
  21. params_shard_111.bin +3 -0
  22. params_shard_112.bin +3 -0
  23. params_shard_113.bin +3 -0
  24. params_shard_114.bin +3 -0
  25. params_shard_115.bin +3 -0
  26. params_shard_116.bin +3 -0
  27. params_shard_117.bin +3 -0
  28. params_shard_118.bin +3 -0
  29. params_shard_119.bin +3 -0
  30. params_shard_12.bin +3 -0
  31. params_shard_120.bin +3 -0
  32. params_shard_121.bin +3 -0
  33. params_shard_122.bin +3 -0
  34. params_shard_123.bin +3 -0
  35. params_shard_124.bin +3 -0
  36. params_shard_125.bin +3 -0
  37. params_shard_126.bin +3 -0
  38. params_shard_127.bin +3 -0
  39. params_shard_128.bin +3 -0
  40. params_shard_129.bin +3 -0
  41. params_shard_13.bin +3 -0
  42. params_shard_130.bin +3 -0
  43. params_shard_131.bin +3 -0
  44. params_shard_132.bin +3 -0
  45. params_shard_133.bin +3 -0
  46. params_shard_134.bin +3 -0
  47. params_shard_135.bin +3 -0
  48. params_shard_136.bin +3 -0
  49. params_shard_137.bin +3 -0
  50. params_shard_138.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
mlc-chat-config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "gemma3",
4
+ "quantization": "q4f32_1",
5
+ "model_config": {
6
+ "text_config": {
7
+ "hidden_size": 3840,
8
+ "intermediate_size": 15360,
9
+ "num_hidden_layers": 48,
10
+ "attention_bias": false,
11
+ "num_attention_heads": 16,
12
+ "num_key_value_heads": 8,
13
+ "head_dim": 256,
14
+ "rms_norm_eps": 1e-06,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "position_embedding_base": 10000,
17
+ "context_window_size": 8192,
18
+ "prefill_chunk_size": 8192,
19
+ "query_pre_attn_scalar": 256,
20
+ "sliding_window": 1024,
21
+ "kwargs": {
22
+ "model_type": "gemma3_text",
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "rope_type": "linear"
26
+ }
27
+ }
28
+ },
29
+ "vocab_size": 262208,
30
+ "tensor_parallel_shards": 1,
31
+ "max_batch_size": 128,
32
+ "context_window_size": 8192,
33
+ "sliding_window_size": -1,
34
+ "prefill_chunk_size": 8192,
35
+ "is_text_model": false
36
+ },
37
+ "vocab_size": 262208,
38
+ "context_window_size": 8192,
39
+ "sliding_window_size": -1,
40
+ "prefill_chunk_size": 8192,
41
+ "attention_sink_size": -1,
42
+ "tensor_parallel_shards": 1,
43
+ "pipeline_parallel_stages": 1,
44
+ "temperature": 1.0,
45
+ "presence_penalty": 0.0,
46
+ "frequency_penalty": 0.0,
47
+ "repetition_penalty": 1.0,
48
+ "top_p": 0.95,
49
+ "tokenizer_files": [
50
+ "tokenizer.model",
51
+ "tokenizer.json",
52
+ "added_tokens.json",
53
+ "tokenizer_config.json"
54
+ ],
55
+ "tokenizer_info": {
56
+ "token_postproc_method": "byte_fallback",
57
+ "prepend_space_in_encode": false,
58
+ "strip_space_in_decode": false
59
+ },
60
+ "conv_template": {
61
+ "name": "gemma_instruction",
62
+ "system_template": "{system_message}",
63
+ "system_message": "",
64
+ "system_prefix_token_ids": [
65
+ 2
66
+ ],
67
+ "add_role_after_system_message": true,
68
+ "roles": {
69
+ "user": "<start_of_turn>user",
70
+ "assistant": "<start_of_turn>model"
71
+ },
72
+ "role_templates": {
73
+ "user": "{user_message}",
74
+ "assistant": "{assistant_message}",
75
+ "tool": "{tool_message}"
76
+ },
77
+ "messages": [],
78
+ "seps": [
79
+ "<end_of_turn>\n"
80
+ ],
81
+ "role_content_sep": "\n",
82
+ "role_empty_sep": "\n",
83
+ "stop_str": [
84
+ "<end_of_turn>"
85
+ ],
86
+ "stop_token_ids": [
87
+ 1,
88
+ 107
89
+ ],
90
+ "function_string": "",
91
+ "use_function_calling": false
92
+ },
93
+ "pad_token_id": 0,
94
+ "bos_token_id": 2,
95
+ "eos_token_id": [
96
+ 1,
97
+ 106
98
+ ]
99
+ }
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:f2ee47b6a918a71402adcd730372a8bdad4e52c060cef03aed3477f56325bb3d
3
+ size 503439360
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:734f6e04a3299f70ff6aeeb8fcc6a7b837a24314cf7c1fbabf1a3742a394a788
3
+ size 62929920
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:396b208e09cd21b9799d2588558f1ba8ca09202a4dc785f9caa5a47d82e98911
3
+ size 28785664
params_shard_100.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:718807519e3c3cd375523a9b32c64cbe6cb3ec8842c0f65e5dbe31f773513b98
3
+ size 33447424
params_shard_101.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d475d1279bf198d5ef6bfa77a9f40ab2eb39c9c7380e8b1809a4605d8575969
3
+ size 29990400
params_shard_102.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce409868a361c4b7816d081b053f1e4be190c56e26f72f933706baf87bb5b35
3
+ size 58982400
params_shard_103.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6280237c3fddd6b9700f7628fdefbde666587e79330e43e981fe6bd3ce73b05c
3
+ size 33201664
params_shard_104.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2fc198d35a7d7286f125e00d9f4b6e88e219b8320a572d2193d538e924df955
3
+ size 29491200
params_shard_105.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892b1a3a07eb4923a366baa97642686ebf8e6ec3b468f08e9c730866ee7101aa
3
+ size 58982400
params_shard_106.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7c2a575dbb27512cf84bf5ab717a06245bb9b0f7989702d992986f7bc76ea9
3
+ size 28785664
params_shard_107.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7583cebadbb4d1b32d8c1eed9d59f982d906c8339eecc5c3f534a247e187ca47
3
+ size 29491200
params_shard_108.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86b7e76c10f5ee337ca5b3372aa00c8eea123537aee9e93df4537fc9de234e9
3
+ size 58982400
params_shard_109.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd7110ffc2eea9255c558ad18fda3010323be95cf8f10b452aaecd8101ec04f
3
+ size 28785152
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c5d84556978db436a79436d820e2b88ae7136c510e681648b6cbc986c2985b
3
+ size 29491200
params_shard_110.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6388f6f719e1fcbaf74549782bb952fc0af1c3a3fc9fdedca3fb4cd218e6cc
3
+ size 29491200
params_shard_111.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c54b929f110696fe8525ba0718196011f36a3c0efa8d3a99597a12aea052cbe
3
+ size 58982400
params_shard_112.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2cba3420a84644ffc2636f624e06cf2f460106c523cb4bce9b63cb6dedca750
3
+ size 33209344
params_shard_113.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3694f30a19e57ee782b90afdda376acbb1a66582127d13d5519675809e45d853
3
+ size 29491200
params_shard_114.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89d26be3626fc7db26e4371d71c2d4039502b3ab2264cd4f9a91e598b50eff50
3
+ size 58982400
params_shard_115.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03855ef30571affba9ea76f17a215d6158bdd548833b9929292fe8e7fcf1d188
3
+ size 30236672
params_shard_116.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e819efabe3807e53e61ff1075cecdb01536c1bcd66a7c2abfdc93bb87fa0e4
3
+ size 33447424
params_shard_117.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e9b3510fce4ca51c7120e89668df695f407cd018b010fdd001c2e735bc7ce5a
3
+ size 29990400
params_shard_118.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3b12b81867f8cf2f4180ce45ab6d92e875c49b401d0def82656059ffc5fc5d2
3
+ size 58982400
params_shard_119.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca07f3fa95ae5a407ad64367a0aa3d9219167c61b50611017c2a3c0b5ef3c568
3
+ size 33201664
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80877006f3aa537ce68bff1f11821635ade816db6a32c4ca02616d18b6d43a22
3
+ size 58982400
params_shard_120.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09caf987848425d3488ba7867b2972ba0e0bd4f9f2972bb690a0ed50a7cc08b3
3
+ size 58982400
params_shard_121.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b32f25d75ba49d03256b23ee3de6bd5306f5bc5bd73aaaa4e144df5f682510e
3
+ size 32932864
params_shard_122.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d1532fe0a8fbbbc674ac0a21a9a91a70c72fc0edb57b899810b2c51a318d08f
3
+ size 29491200
params_shard_123.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:915fc3d3b3c2d376502337edafa8c6a55cf1c933d98346644b7ab8a91ea3efe4
3
+ size 29491200
params_shard_124.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab9d3d5f6c5a75e375db588b4c8443bad28497df55eebdb0123745dc1040564
3
+ size 58982400
params_shard_125.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e04f7bfcc05de20f8558380c1e28af3ea5d2e496b0261a42813338c52b1b6b
3
+ size 33485824
params_shard_126.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d4e26eda8163f1a493fb5abb5a31241af1d298a3c0348e1143679b1d348ad3e
3
+ size 29491200
params_shard_127.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229d2b8770c8259536c4dc1a1fb3c2f6873d68fd8a23e11dd7046ce6d5e357cc
3
+ size 58982400
params_shard_128.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d76fe2d3b220009a9eb9167df0266074762695b4e971b0342aae9032d9a67b
3
+ size 28785152
params_shard_129.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b3a5ab8bc8a3d9ed1e97a4d8970dd94dc78389512952c9f436ec3f55a2fdd0
3
+ size 29491200
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad6e1e00d1b8a1d6a2d72f2667e3770cb71f1d059abe242eff5a54218d227f6
3
+ size 28785152
params_shard_130.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62cadefbe5f322ade903181e3728259678bd24b2045de1277bc20546f4153001
3
+ size 58982400
params_shard_131.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d58aa9ab9663ff3c370e42f52d779c320191618859f69b2f3b1c12504c0ab20
3
+ size 33209344
params_shard_132.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9d3ab758573928e64e3c0580a3537afca01dd497d908beadb18e7e1e81aa7b
3
+ size 29491200
params_shard_133.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065b15f1e63472c7b0743d5291ea3c5b202f39a69a89344237b0bd2a58dfa585
3
+ size 58982400
params_shard_134.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ef3d3145342b4b2eb0105740bb580903a58f28157dca43deb1e8f24ed432658
3
+ size 30236672
params_shard_135.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:690ce6660be31b77ff8697f51fcb2fa27a9d53d4444780b3d4722e1a4b6781ff
3
+ size 33447424
params_shard_136.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd53fa68046b464f6dcd2203b94b7447797ba28ade5e848a720f3d941ebc2007
3
+ size 29990400
params_shard_137.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:784f661a6e0247ec0e1e4a8c476f1e50b3352f2b2fa3f47c7f9fcc38a4493136
3
+ size 58982400
params_shard_138.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21a6b6cdfd7a6147c91c4ef490c1284f8038e16b30d2f842358530f1f83ed49
3
+ size 33201664