vikramlingam commited on
Commit
e91ac4a
·
verified ·
1 Parent(s): 414b04e

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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
  gemma-3-270m-it-mlc/tokenizer.json 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
  gemma-3-270m-it-mlc/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ gemma-3-270m-it-mlc/resolve/main/tokenizer.json filter=lfs diff=lfs merge=lfs -text
gemma-3-270m-it-mlc/mlc-chat-config.json CHANGED
@@ -18,7 +18,7 @@
18
  "context_window_size": 8192,
19
  "prefill_chunk_size": 8192,
20
  "query_pre_attn_scalar": 256,
21
- "sliding_window_size": 512,
22
  "kwargs": {
23
  "_sliding_window_pattern": 6,
24
  "architectures": [
@@ -71,7 +71,7 @@
71
  },
72
  "vocab_size": 262144,
73
  "context_window_size": 8192,
74
- "sliding_window_size": 512,
75
  "prefill_chunk_size": 8192,
76
  "attention_sink_size": -1,
77
  "tensor_parallel_shards": 1,
@@ -94,7 +94,7 @@
94
  "strip_space_in_decode": false
95
  },
96
  "conv_template": {
97
- "name": "gemma_instruction",
98
  "system_template": "{system_message}",
99
  "system_message": "",
100
  "system_prefix_token_ids": [
@@ -121,7 +121,7 @@
121
  ],
122
  "stop_token_ids": [
123
  1,
124
- 107
125
  ],
126
  "function_string": "",
127
  "use_function_calling": false
 
18
  "context_window_size": 8192,
19
  "prefill_chunk_size": 8192,
20
  "query_pre_attn_scalar": 256,
21
+ "sliding_window_size": -1,
22
  "kwargs": {
23
  "_sliding_window_pattern": 6,
24
  "architectures": [
 
71
  },
72
  "vocab_size": 262144,
73
  "context_window_size": 8192,
74
+ "sliding_window_size": -1,
75
  "prefill_chunk_size": 8192,
76
  "attention_sink_size": -1,
77
  "tensor_parallel_shards": 1,
 
94
  "strip_space_in_decode": false
95
  },
96
  "conv_template": {
97
+ "name": "gemma3_instruction",
98
  "system_template": "{system_message}",
99
  "system_message": "",
100
  "system_prefix_token_ids": [
 
121
  ],
122
  "stop_token_ids": [
123
  1,
124
+ 106
125
  ],
126
  "function_string": "",
127
  "use_function_calling": false
gemma-3-270m-it-mlc/resolve/main/mlc-chat-config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "gemma3_text",
4
+ "quantization": "q4f16_1",
5
+ "model_config": {
6
+ "text_config": {
7
+ "hidden_size": 640,
8
+ "intermediate_size": 2048,
9
+ "num_hidden_layers": 18,
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": 1000000.0,
17
+ "rope_scaling": null,
18
+ "context_window_size": 8192,
19
+ "prefill_chunk_size": 8192,
20
+ "query_pre_attn_scalar": 256,
21
+ "sliding_window_size": -1,
22
+ "kwargs": {
23
+ "_sliding_window_pattern": 6,
24
+ "architectures": [
25
+ "Gemma3ForCausalLM"
26
+ ],
27
+ "attention_dropout": 0.0,
28
+ "attn_logit_softcapping": null,
29
+ "bos_token_id": 2,
30
+ "eos_token_id": 1,
31
+ "final_logit_softcapping": null,
32
+ "initializer_range": 0.02,
33
+ "layer_types": [
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "full_attention"
52
+ ],
53
+ "max_position_embeddings": 32768,
54
+ "model_type": "gemma3_text",
55
+ "pad_token_id": 0,
56
+ "rope_local_base_freq": 10000.0,
57
+ "sliding_window": 512,
58
+ "torch_dtype": "bfloat16",
59
+ "transformers_version": "4.55.0.dev0",
60
+ "use_bidirectional_attention": false,
61
+ "use_cache": true
62
+ }
63
+ },
64
+ "vocab_size": 262144,
65
+ "tensor_parallel_shards": 1,
66
+ "max_batch_size": 128,
67
+ "context_window_size": 8192,
68
+ "sliding_window_size": 512,
69
+ "prefill_chunk_size": 8192,
70
+ "is_text_model": true
71
+ },
72
+ "vocab_size": 262144,
73
+ "context_window_size": 8192,
74
+ "sliding_window_size": -1,
75
+ "prefill_chunk_size": 8192,
76
+ "attention_sink_size": -1,
77
+ "tensor_parallel_shards": 1,
78
+ "pipeline_parallel_stages": 1,
79
+ "active_vocab_size": 262145,
80
+ "temperature": 1.0,
81
+ "presence_penalty": 0.0,
82
+ "frequency_penalty": 0.0,
83
+ "repetition_penalty": 1.0,
84
+ "top_p": 0.95,
85
+ "tokenizer_files": [
86
+ "tokenizer.model",
87
+ "tokenizer.json",
88
+ "added_tokens.json",
89
+ "tokenizer_config.json"
90
+ ],
91
+ "tokenizer_info": {
92
+ "token_postproc_method": "byte_fallback",
93
+ "prepend_space_in_encode": false,
94
+ "strip_space_in_decode": false
95
+ },
96
+ "conv_template": {
97
+ "name": "gemma3_instruction",
98
+ "system_template": "{system_message}",
99
+ "system_message": "",
100
+ "system_prefix_token_ids": [
101
+ 2
102
+ ],
103
+ "add_role_after_system_message": true,
104
+ "roles": {
105
+ "user": "<start_of_turn>user",
106
+ "assistant": "<start_of_turn>model"
107
+ },
108
+ "role_templates": {
109
+ "user": "{user_message}",
110
+ "assistant": "{assistant_message}",
111
+ "tool": "{tool_message}"
112
+ },
113
+ "messages": [],
114
+ "seps": [
115
+ "<end_of_turn>\n"
116
+ ],
117
+ "role_content_sep": "\n",
118
+ "role_empty_sep": "\n",
119
+ "stop_str": [
120
+ "<end_of_turn>"
121
+ ],
122
+ "stop_token_ids": [
123
+ 1,
124
+ 106
125
+ ],
126
+ "function_string": "",
127
+ "use_function_calling": false
128
+ },
129
+ "pad_token_id": 0,
130
+ "bos_token_id": 2,
131
+ "eos_token_id": [
132
+ 1,
133
+ 106
134
+ ]
135
+ }
gemma-3-270m-it-mlc/resolve/main/ndarray-cache.json ADDED
The diff for this file is too large to render. See raw diff
 
gemma-3-270m-it-mlc/resolve/main/params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05be779dd1c57a82d36f3700e0f1bf8f86e4758e00db15ac99637283ddee226e
3
+ size 83886080
gemma-3-270m-it-mlc/resolve/main/params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff50558747fc833937f16e7b8770e4f1ab1ca75cf49f96bd85218a18dd1c55e
3
+ size 33201408
gemma-3-270m-it-mlc/resolve/main/params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9490a0f1bcd1d75ce34ca4312bacf253fd6b6b4ac4ed4309ceece785e6e534b6
3
+ size 33336064
gemma-3-270m-it-mlc/resolve/main/params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd665c36340dc7166687278c78fa7c9f1196defe73219fe3fa08f0201667a38
3
+ size 462080
gemma-3-270m-it-mlc/resolve/main/tensor-cache.json ADDED
The diff for this file is too large to render. See raw diff
 
gemma-3-270m-it-mlc/resolve/main/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4046bf0505a327dd5a0abbb427ecd4fc82f99c2ceaa170bc61ecde12809b0c
3
+ size 33384570
gemma-3-270m-it-mlc/resolve/main/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
gemma-3-270m-it-mlc/resolve/main/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff