Delete split_files/tokenizer
Browse files
split_files/tokenizer/chat_template.jinja
DELETED
|
@@ -1,89 +0,0 @@
|
|
| 1 |
-
{%- if tools %}
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0].role == 'system' %}
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
-
{%- for message in messages[::-1] %}
|
| 19 |
-
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
-
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
-
{%- set ns.multi_step_tool = false %}
|
| 22 |
-
{%- set ns.last_query_index = index %}
|
| 23 |
-
{%- endif %}
|
| 24 |
-
{%- endfor %}
|
| 25 |
-
{%- for message in messages %}
|
| 26 |
-
{%- if message.content is string %}
|
| 27 |
-
{%- set content = message.content %}
|
| 28 |
-
{%- else %}
|
| 29 |
-
{%- set content = '' %}
|
| 30 |
-
{%- endif %}
|
| 31 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
-
{%- elif message.role == "assistant" %}
|
| 34 |
-
{%- set reasoning_content = '' %}
|
| 35 |
-
{%- if message.reasoning_content is string %}
|
| 36 |
-
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
-
{%- else %}
|
| 38 |
-
{%- if '</think>' in content %}
|
| 39 |
-
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
-
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
-
{%- endif %}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
-
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
-
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
-
{%- else %}
|
| 47 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 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 %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
split_files/tokenizer/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
-
size 11422650
|
|
|
|
|
|
|
|
|
|
|
|
split_files/tokenizer/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": null,
|
| 5 |
-
"clean_up_tokenization_spaces": false,
|
| 6 |
-
"eos_token": "<|im_end|>",
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"extra_special_tokens": {
|
| 9 |
-
"im_start": "<|im_start|>",
|
| 10 |
-
"im_end": "<|im_end|>",
|
| 11 |
-
"object_ref_start": "<|object_ref_start|>",
|
| 12 |
-
"object_ref_end": "<|object_ref_end|>",
|
| 13 |
-
"box_start": "<|box_start|>",
|
| 14 |
-
"box_end": "<|box_end|>",
|
| 15 |
-
"quad_start": "<|quad_start|>",
|
| 16 |
-
"quad_end": "<|quad_end|>",
|
| 17 |
-
"vision_start": "<|vision_start|>",
|
| 18 |
-
"vision_end": "<|vision_end|>",
|
| 19 |
-
"vision_pad": "<|vision_pad|>",
|
| 20 |
-
"image_pad": "<|image_pad|>",
|
| 21 |
-
"video_pad": "<|video_pad|>"
|
| 22 |
-
},
|
| 23 |
-
"is_local": false,
|
| 24 |
-
"model_max_length": 131072,
|
| 25 |
-
"pad_token": "<|endoftext|>",
|
| 26 |
-
"split_special_tokens": false,
|
| 27 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|