Upload tokenizer
Browse files- .gitattributes +1 -0
- chat_template.jinja +111 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip 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
|
|
|
|
33 |
*.zip 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
|
chat_template.jinja
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{{- bos_token }}
|
2 |
+
{%- if custom_tools is defined and custom_tools%}
|
3 |
+
{%- set tools = custom_tools %}
|
4 |
+
{%- endif %}
|
5 |
+
{%- if tools is defined and tools %}
|
6 |
+
{%- set tool_definition = tool_definition ~ (tools | tojson(indent=4)) %}
|
7 |
+
{%- else %}
|
8 |
+
{%- set tools = none %}
|
9 |
+
{%- endif %}
|
10 |
+
|
11 |
+
|
12 |
+
{#- This block extracts the system message, so we can slot it into the right place. #}
|
13 |
+
{%- if messages[0]['role'] == 'system' %}
|
14 |
+
{%- set user_provided_system_message = true %}
|
15 |
+
{%- if messages[0]['content'] is string %}
|
16 |
+
{%- set system_message = messages[0]['content']|trim %}
|
17 |
+
{%- else %}
|
18 |
+
{%- set system_message = messages[0]['content'][0]['text']|trim %}
|
19 |
+
{%- endif %}
|
20 |
+
{%- set messages = messages[1:] %}
|
21 |
+
{%- else %}
|
22 |
+
{%- if tools is not none %}
|
23 |
+
{#- Since not system_message was provided by user, if tool is provided, system_message is now default tool system message #}
|
24 |
+
{#- This system message is from llama website:https://www.llama.com/docs/model-cards-and-prompt-formats/llama4/ #}
|
25 |
+
{%- set system_message = "You are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n" %}
|
26 |
+
{%- else %}
|
27 |
+
{%- set system_message = "" %}
|
28 |
+
{%- endif %}
|
29 |
+
{%- endif %}
|
30 |
+
{#- Now writing the system message: use the user provided system message if user_provided_system_message, else default tool system message if tools presented #}
|
31 |
+
{%- if system_message %}
|
32 |
+
{#- always use user provided system message to override default tool system message #}
|
33 |
+
{{- "<|header_start|>system<|header_end|>\n\n" }}
|
34 |
+
{{- system_message }}
|
35 |
+
{%- if user_provided_system_message and tools %}
|
36 |
+
{{- "\nHere is a list of functions in JSON format that you can invoke. Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\n" }}
|
37 |
+
{{- tool_definition -}}
|
38 |
+
{%- elif tool_definition %}
|
39 |
+
{{- tool_definition -}}
|
40 |
+
{%- endif %}
|
41 |
+
{{- "<|eot|>" }}
|
42 |
+
{%- endif %}
|
43 |
+
|
44 |
+
{#- Now deal with all other messages #}
|
45 |
+
{%- for message in messages %}
|
46 |
+
{#- Base case: messages that are not from tool role and has empty tool_call list #}
|
47 |
+
{%- if not (message.role == 'ipython' or message.role == 'tool' or ('tool_calls' in message and message.tool_calls|length != 0 )) %}
|
48 |
+
{{- '<|header_start|>' + message['role'] + '<|header_end|>\n\n' }}
|
49 |
+
{%- if message['content'] is string %}
|
50 |
+
{{- message['content'] }}
|
51 |
+
{%- else %}
|
52 |
+
{%- for content in message['content'] %}
|
53 |
+
{%- if content['type'] == 'image' %}
|
54 |
+
{{- '<|image|>' }}
|
55 |
+
{%- elif content['type'] == 'text' %}
|
56 |
+
{{- content['text'] | trim }}
|
57 |
+
{%- endif %}
|
58 |
+
{%- endfor %}
|
59 |
+
{%- endif %}
|
60 |
+
{{- "<|eot|>" }}
|
61 |
+
{#- Tool case: messages has non-empty tool_call list, must from assistant #}
|
62 |
+
{%- elif 'tool_calls' in message %}
|
63 |
+
{#- assume tool_calls are always coming from assistant #}
|
64 |
+
{%- if message.role == 'assistant' %}
|
65 |
+
{{- '<|header_start|>assistant<|header_end|>\n\n' -}}
|
66 |
+
{%- if message['content'] is string %}
|
67 |
+
{{- message['content'] }}
|
68 |
+
{%- else %}
|
69 |
+
{%- for content in message['content'] %}
|
70 |
+
{%- if content['type'] == 'image' %}
|
71 |
+
{{- '<|image|>' }}
|
72 |
+
{%- elif content['type'] == 'text' %}
|
73 |
+
{{- content['text'] }}
|
74 |
+
{%- endif %}
|
75 |
+
{%- endfor %}
|
76 |
+
{%- endif %}
|
77 |
+
{{- "[" }}
|
78 |
+
{%- for tool_call in message.tool_calls %}
|
79 |
+
{%- if tool_call.function is defined %}
|
80 |
+
{%- set tool_call = tool_call.function %}
|
81 |
+
{%- endif %}
|
82 |
+
{{- tool_call.name + '(' -}}
|
83 |
+
{%- for param in tool_call.arguments %}
|
84 |
+
{{- param + '="' -}}
|
85 |
+
{{- "%s" | format(tool_call.arguments[param]) -}}
|
86 |
+
{{- '"' -}}
|
87 |
+
{% if not loop.last %}, {% endif %}
|
88 |
+
{%- endfor %}
|
89 |
+
{{- ')' -}}
|
90 |
+
{% if not loop.last %}, {% endif %}
|
91 |
+
{%- endfor %}
|
92 |
+
{{- "]<|eot|>" }}
|
93 |
+
{%- endif %}
|
94 |
+
{#- Tool_response case: messages are from tool_response #}
|
95 |
+
{%- elif message.role == "tool" or message.role == "ipython" %}
|
96 |
+
{{- "<|header_start|>ipython<|header_end|>\n\n" }}
|
97 |
+
{%- if message.content is string %}
|
98 |
+
{{- message.content | tojson }}
|
99 |
+
{%- else %}
|
100 |
+
{%- for content in message['content'] %}
|
101 |
+
{%- if content['type'] == 'text' %}
|
102 |
+
{{- content['text'] | tojson }}
|
103 |
+
{%- endif %}
|
104 |
+
{%- endfor %}
|
105 |
+
{%- endif %}
|
106 |
+
{{- "<|eot|>" }}
|
107 |
+
{%- endif %}
|
108 |
+
{%- endfor %}
|
109 |
+
{%- if add_generation_prompt %}
|
110 |
+
{{- '<|header_start|>assistant<|header_end|>\n\n' }}
|
111 |
+
{%- endif %}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|finetune_right_pad|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:172c9eb4beafc72601690da3ccfcede5c2e6806a8d5ec1fca33e22acea8023a4
|
3 |
+
size 27948578
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|