Upload tokenizer
Browse files- added_tokens.json +1 -26
- chat_template.jinja +47 -89
- special_tokens_map.json +19 -17
- tokenizer.json +2 -2
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
added_tokens.json
CHANGED
|
@@ -1,28 +1,3 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"</tool_call>": 151658,
|
| 4 |
-
"</tool_response>": 151666,
|
| 5 |
-
"<think>": 151667,
|
| 6 |
-
"<tool_call>": 151657,
|
| 7 |
-
"<tool_response>": 151665,
|
| 8 |
-
"<|box_end|>": 151649,
|
| 9 |
-
"<|box_start|>": 151648,
|
| 10 |
-
"<|endoftext|>": 151643,
|
| 11 |
-
"<|file_sep|>": 151664,
|
| 12 |
-
"<|fim_middle|>": 151660,
|
| 13 |
-
"<|fim_pad|>": 151662,
|
| 14 |
-
"<|fim_prefix|>": 151659,
|
| 15 |
-
"<|fim_suffix|>": 151661,
|
| 16 |
-
"<|im_end|>": 151645,
|
| 17 |
-
"<|im_start|>": 151644,
|
| 18 |
-
"<|image_pad|>": 151655,
|
| 19 |
-
"<|object_ref_end|>": 151647,
|
| 20 |
-
"<|object_ref_start|>": 151646,
|
| 21 |
-
"<|quad_end|>": 151651,
|
| 22 |
-
"<|quad_start|>": 151650,
|
| 23 |
-
"<|repo_name|>": 151663,
|
| 24 |
-
"<|video_pad|>": 151656,
|
| 25 |
-
"<|vision_end|>": 151653,
|
| 26 |
-
"<|vision_pad|>": 151654,
|
| 27 |
-
"<|vision_start|>": 151652
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"<image_soft_token>": 262144
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
}
|
chat_template.jinja
CHANGED
|
@@ -1,89 +1,47 @@
|
|
| 1 |
-
{
|
| 2 |
-
|
| 3 |
-
{%- if messages[0]
|
| 4 |
-
{
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
{%-
|
| 8 |
-
{
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
{
|
| 12 |
-
{%-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
{%-
|
| 16 |
-
{%- endif
|
| 17 |
-
{%-
|
| 18 |
-
{%-
|
| 19 |
-
|
| 20 |
-
{%-
|
| 21 |
-
|
| 22 |
-
{%- set
|
| 23 |
-
{%-
|
| 24 |
-
{%-
|
| 25 |
-
{%-
|
| 26 |
-
{
|
| 27 |
-
|
| 28 |
-
{%-
|
| 29 |
-
{
|
| 30 |
-
{%-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
{%-
|
| 37 |
-
{%-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
{%- endif %}
|
| 49 |
-
{%- else %}
|
| 50 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
-
{%- endif %}
|
| 52 |
-
{%- if message.tool_calls %}
|
| 53 |
-
{%- for tool_call in message.tool_calls %}
|
| 54 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
-
{{- '\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- if tool_call.function %}
|
| 58 |
-
{%- set tool_call = tool_call.function %}
|
| 59 |
-
{%- endif %}
|
| 60 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
-
{{- tool_call.name }}
|
| 62 |
-
{{- '", "arguments": ' }}
|
| 63 |
-
{%- if tool_call.arguments is string %}
|
| 64 |
-
{{- tool_call.arguments }}
|
| 65 |
-
{%- else %}
|
| 66 |
-
{{- tool_call.arguments | tojson }}
|
| 67 |
-
{%- endif %}
|
| 68 |
-
{{- '}\n</tool_call>' }}
|
| 69 |
-
{%- endfor %}
|
| 70 |
-
{%- endif %}
|
| 71 |
-
{{- '<|im_end|>\n' }}
|
| 72 |
-
{%- elif message.role == "tool" %}
|
| 73 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
-
{{- '<|im_start|>user' }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{{- '\n<tool_response>\n' }}
|
| 77 |
-
{{- content }}
|
| 78 |
-
{{- '\n</tool_response>' }}
|
| 79 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
-
{{- '<|im_end|>\n' }}
|
| 81 |
-
{%- endif %}
|
| 82 |
-
{%- endif %}
|
| 83 |
-
{%- endfor %}
|
| 84 |
-
{%- if add_generation_prompt %}
|
| 85 |
-
{{- '<|im_start|>assistant\n' }}
|
| 86 |
-
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
-
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
-
{%- endif %}
|
| 89 |
-
{%- endif %}
|
|
|
|
| 1 |
+
{{ bos_token }}
|
| 2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
| 3 |
+
{%- if messages[0]['content'] is string -%}
|
| 4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 5 |
+
|
| 6 |
+
' -%}
|
| 7 |
+
{%- else -%}
|
| 8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
| 9 |
+
|
| 10 |
+
' -%}
|
| 11 |
+
{%- endif -%}
|
| 12 |
+
{%- set loop_messages = messages[1:] -%}
|
| 13 |
+
{%- else -%}
|
| 14 |
+
{%- set first_user_prefix = "" -%}
|
| 15 |
+
{%- set loop_messages = messages -%}
|
| 16 |
+
{%- endif -%}
|
| 17 |
+
{%- for message in loop_messages -%}
|
| 18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 20 |
+
{%- endif -%}
|
| 21 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 22 |
+
{%- set role = "model" -%}
|
| 23 |
+
{%- else -%}
|
| 24 |
+
{%- set role = message['role'] -%}
|
| 25 |
+
{%- endif -%}
|
| 26 |
+
{{ '<start_of_turn>' + role + '
|
| 27 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 28 |
+
{%- if message['content'] is string -%}
|
| 29 |
+
{{ message['content'] | trim }}
|
| 30 |
+
{%- elif message['content'] is iterable -%}
|
| 31 |
+
{%- for item in message['content'] -%}
|
| 32 |
+
{%- if item['type'] == 'image' -%}
|
| 33 |
+
{{ '<start_of_image>' }}
|
| 34 |
+
{%- elif item['type'] == 'text' -%}
|
| 35 |
+
{{ item['text'] | trim }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
{%- else -%}
|
| 39 |
+
{{ raise_exception("Invalid content type") }}
|
| 40 |
+
{%- endif -%}
|
| 41 |
+
{{ '<end_of_turn>
|
| 42 |
+
' }}
|
| 43 |
+
{%- endfor -%}
|
| 44 |
+
{%- if add_generation_prompt -%}
|
| 45 |
+
{{'<start_of_turn>model
|
| 46 |
+
'}}
|
| 47 |
+
{%- endif -%}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,28 +1,30 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
"<|vision_start|>",
|
| 12 |
-
"<|vision_end|>",
|
| 13 |
-
"<|vision_pad|>",
|
| 14 |
-
"<|image_pad|>",
|
| 15 |
-
"<|video_pad|>"
|
| 16 |
-
],
|
| 17 |
"eos_token": {
|
| 18 |
-
"content": "
|
| 19 |
"lstrip": false,
|
| 20 |
"normalized": false,
|
| 21 |
"rstrip": false,
|
| 22 |
"single_word": false
|
| 23 |
},
|
|
|
|
| 24 |
"pad_token": {
|
| 25 |
-
"content": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"lstrip": false,
|
| 27 |
"normalized": false,
|
| 28 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"boi_token": "<start_of_image>",
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"eoi_token": "<end_of_image>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"eos_token": {
|
| 12 |
+
"content": "<end_of_turn>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false
|
| 17 |
},
|
| 18 |
+
"image_token": "<image_soft_token>",
|
| 19 |
"pad_token": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
"lstrip": false,
|
| 29 |
"normalized": false,
|
| 30 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|