Buildwellai commited on
Commit
ed65e6e
·
verified ·
1 Parent(s): a21881a

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +26 -26
tokenizer_config.json CHANGED
@@ -3,33 +3,33 @@
3
  "add_eos_token": false,
4
  "add_prefix_space": null,
5
  "auto_map": {
6
- "AutoConfig": [
7
- "configuration_qwen2.Qwen2Config",
8
- "qwen2_config.Qwen2Config"
9
- ],
10
- "AutoModel": [
11
- "modeling_qwen2.Qwen2Model",
12
- "qwen2.Qwen2ForCausalLM"
13
- ],
14
- "AutoModelForCausalLM": [
15
- "modeling_qwen2.Qwen2ForCausalLM",
16
- "qwen2.Qwen2ForCausalLM"
17
- ],
18
- "AutoModelForQuestionAnswering": [
19
- "modeling_qwen2.Qwen2ForQuestionAnswering",
20
- "qwen2.Qwen2ForQuestionAnswering"
21
- ],
22
- "AutoModelForSequenceClassification": [
23
- "modeling_qwen2.Qwen2ForSequenceClassification",
24
- "qwen2.Qwen2ForSequenceClassification"
25
- ],
26
- "AutoModelForTokenClassification": [
27
- "modeling_qwen2.Qwen2ForTokenClassification",
28
- "qwen2.Qwen2ForTokenClassification"
29
- ]
30
  },
31
  "bos_token": "<|begin_of_text|>",
32
- "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>:' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|>:<|tool_calls|>:<|tool_call|>:' + tool['type'] + '<|tool_sep|>:' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool_call_end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool_call|>:' + tool['type'] + '<|tool_sep|>:' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool_call_end|>'}}{{'<|tool_calls_end|>:<|end_of_text|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool_outputs_end|>:' + message['content'] + '<|end_of_text|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>:' + content + '<|end_of_text|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool_outputs|>:<|tool_output|>:' + message['content'] + '<|tool_output_end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool_output|>:' + message['content'] + '<|tool_output_end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool_outputs_end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>:'}}{% endif %}",
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "<|end_of_text|>",
35
  "legacy": true,
@@ -38,7 +38,7 @@
38
  "padding_side": "left",
39
  "sp_model_kwargs": {},
40
  "tokenizer_class": "Qwen2Tokenizer",
41
- "transformers_version": "4.36.2",
42
  "trust_remote_code": true,
43
  "unk_token": null,
44
  "use_default_system_prompt": false
 
3
  "add_eos_token": false,
4
  "add_prefix_space": null,
5
  "auto_map": {
6
+ "AutoConfig": [
7
+ "configuration_qwen2.Qwen2Config",
8
+ "qwen2_config.Qwen2Config"
9
+ ],
10
+ "AutoModel": [
11
+ "modeling_qwen2.Qwen2Model",
12
+ "qwen2.Qwen2ForCausalLM"
13
+ ],
14
+ "AutoModelForCausalLM": [
15
+ "modeling_qwen2.Qwen2ForCausalLM",
16
+ "qwen2.Qwen2ForCausalLM"
17
+ ],
18
+ "AutoModelForQuestionAnswering": [
19
+ "modeling_qwen2.Qwen2ForQuestionAnswering",
20
+ "qwen2.Qwen2ForQuestionAnswering"
21
+ ],
22
+ "AutoModelForSequenceClassification": [
23
+ "modeling_qwen2.Qwen2ForSequenceClassification",
24
+ "qwen2.Qwen2ForSequenceClassification"
25
+ ],
26
+ "AutoModelForTokenClassification": [
27
+ "modeling_qwen2.Qwen2ForTokenClassification",
28
+ "qwen2.Qwen2ForTokenClassification"
29
+ ]
30
  },
31
  "bos_token": "<|begin_of_text|>",
32
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>:' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|>:<|tool_calls|>:<|tool_call|>:' + tool['type'] + '<|tool_sep|>:' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool_call_end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool_call|>:' + tool['type'] + '<|tool_sep|>:' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool_call_end|>'}}{{'<|tool_calls_end|>:<|end_of_text|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool_outputs_end|>:' + message['content'] + '<|end_of_text|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>:' + content + '<|end_of_text|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool_outputs|>:<|tool_output|>:' + message['content'] + '<|tool_output_end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool_output|>:' + message['content'] + '<|tool_output_end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool_outputs_end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>:'}}{% endif %}",
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "<|end_of_text|>",
35
  "legacy": true,
 
38
  "padding_side": "left",
39
  "sp_model_kwargs": {},
40
  "tokenizer_class": "Qwen2Tokenizer",
41
+ "transformers_version": "4.36.2",
42
  "trust_remote_code": true,
43
  "unk_token": null,
44
  "use_default_system_prompt": false