riczhou commited on
Commit
1bb38e7
·
verified ·
1 Parent(s): 2803a24

Upload folder using huggingface_hub

Browse files
.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 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "gemma3_text",
4
+ "quantization": "q4f32_1",
5
+ "model_config": {
6
+ "text_config": {
7
+ "hidden_size": 1152,
8
+ "intermediate_size": 6912,
9
+ "num_hidden_layers": 26,
10
+ "attention_bias": false,
11
+ "num_attention_heads": 4,
12
+ "num_key_value_heads": 1,
13
+ "head_dim": 256,
14
+ "rms_norm_eps": 1e-06,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "position_embedding_base": 1000000,
17
+ "context_window_size": 8192,
18
+ "prefill_chunk_size": 8192,
19
+ "query_pre_attn_scalar": 256,
20
+ "sliding_window": 512,
21
+ "kwargs": {
22
+ "architectures": [
23
+ "Gemma3ForCausalLM"
24
+ ],
25
+ "attention_dropout": 0.0,
26
+ "attn_logit_softcapping": null,
27
+ "bos_token_id": 2,
28
+ "cache_implementation": "hybrid",
29
+ "eos_token_id": [
30
+ 1,
31
+ 106
32
+ ],
33
+ "final_logit_softcapping": null,
34
+ "initializer_range": 0.02,
35
+ "max_position_embeddings": 32768,
36
+ "model_type": "gemma3_text",
37
+ "pad_token_id": 0,
38
+ "rope_local_base_freq": 10000,
39
+ "rope_scaling": null,
40
+ "sliding_window_pattern": 6,
41
+ "torch_dtype": "bfloat16",
42
+ "transformers_version": "4.50.0.dev0",
43
+ "use_cache": true
44
+ }
45
+ },
46
+ "vocab_size": 262144,
47
+ "tensor_parallel_shards": 1,
48
+ "max_batch_size": 128,
49
+ "context_window_size": 8192,
50
+ "sliding_window_size": -1,
51
+ "prefill_chunk_size": 8192,
52
+ "is_text_model": true
53
+ },
54
+ "vocab_size": 262144,
55
+ "context_window_size": 8192,
56
+ "sliding_window_size": -1,
57
+ "prefill_chunk_size": 8192,
58
+ "attention_sink_size": -1,
59
+ "tensor_parallel_shards": 1,
60
+ "pipeline_parallel_stages": 1,
61
+ "temperature": 1.0,
62
+ "presence_penalty": 0.0,
63
+ "frequency_penalty": 0.0,
64
+ "repetition_penalty": 1.0,
65
+ "top_p": 0.95,
66
+ "tokenizer_files": [
67
+ "tokenizer.model",
68
+ "tokenizer.json",
69
+ "added_tokens.json",
70
+ "tokenizer_config.json"
71
+ ],
72
+ "tokenizer_info": {
73
+ "token_postproc_method": "byte_fallback",
74
+ "prepend_space_in_encode": false,
75
+ "strip_space_in_decode": false
76
+ },
77
+ "conv_template": {
78
+ "name": "gemma_instruction",
79
+ "system_template": "{system_message}",
80
+ "system_message": "",
81
+ "system_prefix_token_ids": [
82
+ 2
83
+ ],
84
+ "add_role_after_system_message": true,
85
+ "roles": {
86
+ "user": "<start_of_turn>user",
87
+ "assistant": "<start_of_turn>model"
88
+ },
89
+ "role_templates": {
90
+ "user": "{user_message}",
91
+ "assistant": "{assistant_message}",
92
+ "tool": "{tool_message}"
93
+ },
94
+ "messages": [],
95
+ "seps": [
96
+ "<end_of_turn>\n"
97
+ ],
98
+ "role_content_sep": "\n",
99
+ "role_empty_sep": "\n",
100
+ "stop_str": [
101
+ "<end_of_turn>"
102
+ ],
103
+ "stop_token_ids": [
104
+ 1,
105
+ 107
106
+ ],
107
+ "function_string": "",
108
+ "use_function_calling": false
109
+ },
110
+ "pad_token_id": 0,
111
+ "bos_token_id": 2,
112
+ "eos_token_id": [
113
+ 1,
114
+ 106
115
+ ]
116
+ }
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 sha256:5deeec9d5c80ffbbe3d7d6fd12cd971ce487b0dedc4cd25c37df13cfc8488462
3
+ size 150994944
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e724f2ee43ea1450152d8d0be9dcec25d77ebc8b855a9ff21d4e4f27470b6c89
3
+ size 33150976
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:accfe23f203c106844e4f20c9bf6d3531649d66c58daae0056a8e431d6fdadff
3
+ size 30212096
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff49481e83a110a9877e1248495aa75a53bc47b9804979fc416374db61adbfe1
3
+ size 30212096
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b6e69342572f41ca035d5127cbd075cc4f36c08e142d42b8d07502093cbc948
3
+ size 30212096
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b5ba3392cb4d5b765693db40efb643afa76f55727bdd6a7f90657e50051a91
3
+ size 30212096
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3d9033df1b6de163e68d330cd4f2ed760795f6213f581cb9e8e393445c0b87b
3
+ size 15106048
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b543e1440451f1f99ea772352f3d104ed1b4af867960e0f17cc217acb8c93489
3
+ size 31043840
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18cd652a29310eeb7fc19a01c92b1608d60528b6e22e137c80759dc210ea8aab
3
+ size 30212096
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bb9bba69fb4da6cca424ab2ef59844694fdef85ed077079ab19e98fa9f1caa8
3
+ size 30212096
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95581b6262d1b6e2affee8791e449f9cb6b152c2672e61dcf0606a408a7e4e1
3
+ size 30212096
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b37fd79d6648d378702384550822431923e5147b2feb52357b4af348e6dc77d4
3
+ size 30212096
params_shard_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:531cb8889310d97b6117c18c88b749df046c64d50b85dafca1423a2e234a29d0
3
+ size 30212096
params_shard_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:890add83012a2bdb1f3248e4c1e8f9137e313dacec4e6c593c3679212deab2c2
3
+ size 30212096
params_shard_9.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f77402cfda99ada3731b3af3ebfae71dbe7d3a3479e49a34258fb954364a997f
3
+ size 30212096
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff