Add sharded ONNX layout, transformers.js config, and generation config

#1
by yakuraku - opened
.gitattributes CHANGED
@@ -36,3 +36,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
37
  decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
38
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
36
  decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
37
  decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
38
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
40
+ onnx/model.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
41
+ onnx/model.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
42
+ onnx/model.onnx_data_3 filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -25,5 +25,10 @@
25
  "transformers_version": "4.57.3",
26
  "use_cache": false,
27
  "use_qk_norm": true,
28
- "vocab_size": 151936
 
 
 
 
 
29
  }
 
25
  "transformers_version": "4.57.3",
26
  "use_cache": false,
27
  "use_qk_norm": true,
28
+ "vocab_size": 151936,
29
+ "transformers.js_config": {
30
+ "use_external_data_format": {
31
+ "model.onnx": 4
32
+ }
33
+ }
34
  }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token_id": [
3
+ 151643,
4
+ 151645
5
+ ],
6
+ "pad_token_id": 151643
7
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44435a74a48eda79a5f1b288655c56f6c1d2e75b59e50b774445b262b5bf8e86
3
+ size 1677425
onnx/model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60377b980fce2d065236eaa816d3195b633509579947c5a841e527246d743c78
3
+ size 1602385920
onnx/model.onnx_data_1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540cdeba29ee065cfbf394a4e4336d2139e88e3e81f16add49a269c1a12fb70e
3
+ size 1610612736
onnx/model.onnx_data_2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4e4a16bd574f4df599de01e50e4a5a3718936ee32cecd326af2e3879ba20d09
3
+ size 891813888
onnx/model.onnx_data_3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9301a5203af463f0129f995b221340a2f7daf3c39ed6cb6cbe1a0ccbfa7e5135
3
+ size 933494976
tokenizer_config.json CHANGED
@@ -204,5 +204,6 @@
204
  "pad_token": "<|endoftext|>",
205
  "split_special_tokens": false,
206
  "tokenizer_class": "Qwen2Tokenizer",
207
- "unk_token": null
 
208
  }
 
204
  "pad_token": "<|endoftext|>",
205
  "split_special_tokens": false,
206
  "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null,
208
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\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 {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
209
  }