Bharath Kumar Kakumani
commited on
Upload tokenizer
Browse files- .gitattributes +1 -0
- chat_template.jinja +93 -0
- special_tokens_map.json +36 -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 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{- bos_token }}
|
| 2 |
+
{%- if custom_tools is defined %}
|
| 3 |
+
{%- set tools = custom_tools %}
|
| 4 |
+
{%- endif %}
|
| 5 |
+
{%- if not tools_in_user_message is defined %}
|
| 6 |
+
{%- set tools_in_user_message = true %}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{%- if not date_string is defined %}
|
| 9 |
+
{%- if strftime_now is defined %}
|
| 10 |
+
{%- set date_string = strftime_now("%d %b %Y") %}
|
| 11 |
+
{%- else %}
|
| 12 |
+
{%- set date_string = "26 Jul 2024" %}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if not tools is defined %}
|
| 16 |
+
{%- set tools = none %}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
|
| 19 |
+
{#- This block extracts the system message, so we can slot it into the right place. #}
|
| 20 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 21 |
+
{%- set system_message = messages[0]['content']|trim %}
|
| 22 |
+
{%- set messages = messages[1:] %}
|
| 23 |
+
{%- else %}
|
| 24 |
+
{%- set system_message = "" %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
|
| 27 |
+
{#- System message #}
|
| 28 |
+
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
| 29 |
+
{%- if tools is not none %}
|
| 30 |
+
{{- "Environment: ipython\n" }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{{- "Cutting Knowledge Date: December 2023\n" }}
|
| 33 |
+
{{- "Today Date: " + date_string + "\n\n" }}
|
| 34 |
+
{%- if tools is not none and not tools_in_user_message %}
|
| 35 |
+
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
| 36 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 37 |
+
{{- "Do not use variables.\n\n" }}
|
| 38 |
+
{%- for t in tools %}
|
| 39 |
+
{{- t | tojson(indent=4) }}
|
| 40 |
+
{{- "\n\n" }}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- system_message }}
|
| 44 |
+
{{- "<|eot_id|>" }}
|
| 45 |
+
|
| 46 |
+
{#- Custom tools are passed in a user message with some extra guidance #}
|
| 47 |
+
{%- if tools_in_user_message and not tools is none %}
|
| 48 |
+
{#- Extract the first user message so we can plug it in here #}
|
| 49 |
+
{%- if messages | length != 0 %}
|
| 50 |
+
{%- set first_user_message = messages[0]['content']|trim %}
|
| 51 |
+
{%- set messages = messages[1:] %}
|
| 52 |
+
{%- else %}
|
| 53 |
+
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
| 54 |
+
{%- endif %}
|
| 55 |
+
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
| 56 |
+
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
| 57 |
+
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
| 58 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 59 |
+
{{- "Do not use variables.\n\n" }}
|
| 60 |
+
{%- for t in tools %}
|
| 61 |
+
{{- t | tojson(indent=4) }}
|
| 62 |
+
{{- "\n\n" }}
|
| 63 |
+
{%- endfor %}
|
| 64 |
+
{{- first_user_message + "<|eot_id|>"}}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
|
| 67 |
+
{%- for message in messages %}
|
| 68 |
+
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
| 69 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
| 70 |
+
{%- elif 'tool_calls' in message %}
|
| 71 |
+
{%- if not message.tool_calls|length == 1 %}
|
| 72 |
+
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- set tool_call = message.tool_calls[0].function %}
|
| 75 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
| 76 |
+
{{- '{"name": "' + tool_call.name + '", ' }}
|
| 77 |
+
{{- '"parameters": ' }}
|
| 78 |
+
{{- tool_call.arguments | tojson }}
|
| 79 |
+
{{- "}" }}
|
| 80 |
+
{{- "<|eot_id|>" }}
|
| 81 |
+
{%- elif message.role == "tool" or message.role == "ipython" %}
|
| 82 |
+
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
| 83 |
+
{%- if message.content is mapping or message.content is iterable %}
|
| 84 |
+
{{- message.content | tojson }}
|
| 85 |
+
{%- else %}
|
| 86 |
+
{{- message.content }}
|
| 87 |
+
{%- endif %}
|
| 88 |
+
{{- "<|eot_id|>" }}
|
| 89 |
+
{%- endif %}
|
| 90 |
+
{%- endfor %}
|
| 91 |
+
{%- if add_generation_prompt %}
|
| 92 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
| 93 |
+
{%- endif %}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<spk_kavya>",
|
| 4 |
+
"<spk_apsara>",
|
| 5 |
+
"<spk_agastya>",
|
| 6 |
+
"<spk_vinaya>",
|
| 7 |
+
"<spk_maitri>",
|
| 8 |
+
"<spk_charu>",
|
| 9 |
+
"<spk_ishana>",
|
| 10 |
+
"<spk_kyra>",
|
| 11 |
+
"<spk_mohini>",
|
| 12 |
+
"<spk_varun>",
|
| 13 |
+
"<spk_soumya>"
|
| 14 |
+
],
|
| 15 |
+
"bos_token": {
|
| 16 |
+
"content": "<|begin_of_text|>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"eos_token": {
|
| 23 |
+
"content": "<|eot_id|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"pad_token": {
|
| 30 |
+
"content": "<custom_token_7>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c88f202c5216ed6485367f5a606093d54f9a89ef3c654001ccc10026fcd276f2
|
| 3 |
+
size 22851621
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|