Upload optimized ONNX model

#1
by Xenova HF Staff - opened
.gitattributes CHANGED
@@ -34,3 +34,5 @@ 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
  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
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
38
+ onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -59,5 +59,15 @@
59
  "transformers_version": "5.3.0.dev0",
60
  "use_cache": true,
61
  "v_head_dim": 256,
62
- "vocab_size": 154880
63
- }
 
 
 
 
 
 
 
 
 
 
 
59
  "transformers_version": "5.3.0.dev0",
60
  "use_cache": true,
61
  "v_head_dim": 256,
62
+ "vocab_size": 154880,
63
+ "transformers.js_config": {
64
+ "use_external_data_format": {
65
+ "model.onnx": 1,
66
+ "model_fp16.onnx": 1
67
+ },
68
+ "kv_cache_dtype": {
69
+ "q4f16": "float16",
70
+ "fp16": "float16"
71
+ }
72
+ }
73
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d163ef548595cbd596471c82bf683c071d26b358d9a56d2e1a012b3f16eae53
3
+ size 46178
onnx/model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646c58333af47e64b014529ce0d07ef014e1f79d1db188596456033031361c03
3
+ size 65372160
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a231c1960a8a01c403d1267ea7524dc44faf688cbf6185ce78123b767107b5e
3
+ size 49557
onnx/model_fp16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6a4c1a97f77662dd6c5e96fcee0bdf313710333af08469b39a70436ab997c1
3
+ size 32681984
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d
3
- size 20217442
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf00f6d45dc44c710b6ffef0e77f0d004bf142146cc0464c803134d97266284
3
+ size 14755174
tokenizer_config.json CHANGED
@@ -29,5 +29,6 @@
29
  "pad_token": "<|endoftext|>",
30
  "padding_side": "left",
31
  "remove_space": false,
32
- "tokenizer_class": "TokenizersBackend"
33
- }
 
 
29
  "pad_token": "<|endoftext|>",
30
  "padding_side": "left",
31
  "remove_space": false,
32
+ "tokenizer_class": "TokenizersBackend",
33
+ "chat_template": "[gMASK]<sop>\n{%- if tools -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{% for tool in tools %}\n{{ tool | tojson(ensure_ascii=False) }}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content }}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text }}\n {%- elif item is string -%}\n {{- item }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) %}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {% set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{% for m in messages %}\n{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set reasoning_content = '' %}\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n{%- endif %}\n{%- if ((clear_thinking is defined and not clear_thinking) or loop.index0 > ns.last_user_index) and reasoning_content -%}\n{{ '<think>' + reasoning_content.strip() + '</think>'}}\n{%- else -%}\n{{ '</think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n {%- set tc = tc.function %}\n{%- endif %}\n{{- '<tool_call>' + tc.name -}}\n{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if m.content is string -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' }}\n{%- endif %}\n{{- '<tool_response>' }}\n{{- m.content }}\n{{- '</tool_response>' }}\n{%- else -%}\n<|observation|>{% for tr in m.content %}\n<tool_response>{{ tr.output if tr.output is defined else tr }}</tool_response>{% endfor -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|assistant|>{{- '</think>' if (enable_thinking is defined and not enable_thinking) else '<think>' -}}\n{%- endif -%}"
34
+ }