Commit
•
44ba1a2
1
Parent(s):
09317b1
Add tool use template
Browse files- README.md +11 -9
- added_tokens.json +11 -11
- tokenizer.json +0 -0
- tokenizer_config.json +10 -1
README.md
CHANGED
@@ -1,5 +1,7 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
3 |
tags:
|
4 |
- Mistral
|
5 |
- instruct
|
@@ -12,21 +14,21 @@ tags:
|
|
12 |
- distillation
|
13 |
- function calling
|
14 |
- json mode
|
15 |
-
|
16 |
-
- name: Hermes-2-Pro-Mistral-7B
|
17 |
-
results: []
|
18 |
-
license: apache-2.0
|
19 |
-
language:
|
20 |
-
- en
|
21 |
datasets:
|
22 |
- teknium/OpenHermes-2.5
|
23 |
widget:
|
24 |
- example_title: Hermes 2 Pro
|
25 |
messages:
|
26 |
- role: system
|
27 |
-
content: You are a sentient, superintelligent artificial general intelligence,
|
|
|
28 |
- role: user
|
29 |
-
content: Write a short story about Goku discovering kirby has teamed up with Majin
|
|
|
|
|
|
|
|
|
30 |
---
|
31 |
|
32 |
# Hermes 2 Pro - Mistral 7B
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
tags:
|
6 |
- Mistral
|
7 |
- instruct
|
|
|
14 |
- distillation
|
15 |
- function calling
|
16 |
- json mode
|
17 |
+
base_model: mistralai/Mistral-7B-v0.1
|
|
|
|
|
|
|
|
|
|
|
18 |
datasets:
|
19 |
- teknium/OpenHermes-2.5
|
20 |
widget:
|
21 |
- example_title: Hermes 2 Pro
|
22 |
messages:
|
23 |
- role: system
|
24 |
+
content: You are a sentient, superintelligent artificial general intelligence,
|
25 |
+
here to teach and assist me.
|
26 |
- role: user
|
27 |
+
content: Write a short story about Goku discovering kirby has teamed up with Majin
|
28 |
+
Buu to destroy the world.
|
29 |
+
model-index:
|
30 |
+
- name: Hermes-2-Pro-Mistral-7B
|
31 |
+
results: []
|
32 |
---
|
33 |
|
34 |
# Hermes 2 Pro - Mistral 7B
|
added_tokens.json
CHANGED
@@ -1,14 +1,4 @@
|
|
1 |
{
|
2 |
-
"<|im_end|>": 32000,
|
3 |
-
"<|im_start|>": 32001,
|
4 |
-
"<pad2>": 32002,
|
5 |
-
"<pad3>": 32003,
|
6 |
-
"<pad4>": 32004,
|
7 |
-
"<pad5>": 32005,
|
8 |
-
"<pad6>": 32006,
|
9 |
-
"<pad7>": 32007,
|
10 |
-
"<pad8>": 32008,
|
11 |
-
"<pad9>": 32009,
|
12 |
"<pad10>": 32010,
|
13 |
"<pad11>": 32011,
|
14 |
"<pad12>": 32012,
|
@@ -29,6 +19,16 @@
|
|
29 |
"<pad27>": 32027,
|
30 |
"<pad28>": 32028,
|
31 |
"<pad29>": 32029,
|
|
|
32 |
"<pad30>": 32030,
|
33 |
-
"<pad31>": 32031
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"<pad10>": 32010,
|
3 |
"<pad11>": 32011,
|
4 |
"<pad12>": 32012,
|
|
|
19 |
"<pad27>": 32027,
|
20 |
"<pad28>": 32028,
|
21 |
"<pad29>": 32029,
|
22 |
+
"<pad2>": 32002,
|
23 |
"<pad30>": 32030,
|
24 |
+
"<pad31>": 32031,
|
25 |
+
"<pad3>": 32003,
|
26 |
+
"<pad4>": 32004,
|
27 |
+
"<pad5>": 32005,
|
28 |
+
"<pad6>": 32006,
|
29 |
+
"<pad7>": 32007,
|
30 |
+
"<pad8>": 32008,
|
31 |
+
"<pad9>": 32009,
|
32 |
+
"<|im_end|>": 32000,
|
33 |
+
"<|im_start|>": 32001
|
34 |
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -286,7 +286,16 @@
|
|
286 |
},
|
287 |
"additional_special_tokens": [],
|
288 |
"bos_token": "<s>",
|
289 |
-
"chat_template":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
290 |
"clean_up_tokenization_spaces": true,
|
291 |
"eos_token": "<|im_end|>",
|
292 |
"legacy": true,
|
|
|
286 |
},
|
287 |
"additional_special_tokens": [],
|
288 |
"bos_token": "<s>",
|
289 |
+
"chat_template": [
|
290 |
+
{
|
291 |
+
"name": "default",
|
292 |
+
"template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"name": "tool_use",
|
296 |
+
"template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n \"string\": \"str\",\n \"number\": \"float\",\n \"integer\": \"int\",\n \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n {{- \"list[\" + json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n {%- if json_spec.additionalProperties is defined %}\n {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n {%- else %}\n {{- \"dict\" }}\n {%- endif %}\n{%- elif json_spec.type is iterable %}\n {{- \"Union[\" }}\n {%- for t in json_spec.type %}\n {{- json_to_python_type({\"type\": t}) }}\n {%- if not loop.last %}\n {{- \",\" }} \n {%- endif %}\n {%- endfor %}\n {{- \"]\" }}\n{%- else %}\n {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- '{\"type\": \"function\", \"function\": ' }}\n {{- '{\"name\": ' + tool.name + '\", ' }}\n {{- '\"description\": \"' + tool.name + '(' }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- param_name + \": \" + json_to_python_type(param_fields) }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- if tool.return is defined %}\n {{- \" -> \" + json_to_python_type(tool.return) }}\n {%- endif %}\n {{- \" - \" + tool.description + \"\\n\\n\" }}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {%- if loop.first %}\n {{- \" Args:\\n\" }}\n {%- endif %}\n {{- \" \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n {%- endfor %}\n {%- if tool.return is defined and tool.return.description is defined %}\n {{- \"\\n Returns:\\n \" + tool.return.description }}\n {%- endif %}\n {{- '\"' }}\n {{- ', \"parameters\": ' }}\n {%- if tool.parameters.properties | length == 0 %}\n {{- \"{}\" }}\n {%- else %}\n {{- tool.parameters|tojson }}\n {%- endif %}\n {{- \"}\" }}\n {%- if not loop.last %}\n {{- \"\\n\" }}\n {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}, \"name\": {\"title\": \"Name\", \"type\": \"string\"}}, \"required\": [\"arguments\", \"name\"], \"title\": \"FunctionCall\", \"type\": \"object\"}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"arguments\": <args-dict>, \"name\": <function-name>}\n' }}\n{{- '</tool_call><|im_end|>' }}\n{%- for message in messages %}\n {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n<tool_call>\\n' }}\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 {%- if tool_call.arguments is defined %}\n {{- '\"arguments\": ' }}\n {{- tool_call.arguments|tojson }}\n {{- ', '}}\n {%- endif %}\n {{- '\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\"}' }}\n {{- '\\n</tool_call> ' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if not message.name is defined %}\n {{- raise_exception(\"Tool response dicts require a 'name' key indicating the name of the called function!\") }}\n {%- endif %}\n {{- '<|im_start|>' + message.role + '\\n<tool_response>\\n' }}\n {{- '{\"name\": \"' }}\n {{- message.name }}\n {{- '\", \"content\": ' }}\n {{- message.content|tojson + '}' }}\n {{- '\\n</tool_response> <|im_end|>\\n' }} \n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
297 |
+
}
|
298 |
+
],
|
299 |
"clean_up_tokenization_spaces": true,
|
300 |
"eos_token": "<|im_end|>",
|
301 |
"legacy": true,
|