Upload verified Nanbeige4.2 int8 Core AI LanguageBundle
Browse files- .gitattributes +2 -0
- gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/metadata.json +29 -0
- gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/nanbeige4_2_3b_decode_int8hu_block32_sym_s1.aimodel/main.hash +1 -0
- gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/nanbeige4_2_3b_decode_int8hu_block32_sym_s1.aimodel/main.mlirb +3 -0
- gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/nanbeige4_2_3b_decode_int8hu_block32_sym_s1.aimodel/metadata.json +5 -0
- gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/added_tokens.json +9 -0
- gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/chat_template.jinja +195 -0
- gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/special_tokens_map.json +33 -0
- gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/tokenizer.json +3 -0
- gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/tokenizer.model +3 -0
- gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/tokenizer_config.json +102 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ 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 |
+
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/nanbeige4_2_3b_decode_int8hu_block32_sym_s1.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/metadata.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata_version": "0.2",
|
| 3 |
+
"kind": "llm",
|
| 4 |
+
"name": "nanbeige4_2_3b_decode_int8hu_block32_sym_s1",
|
| 5 |
+
"assets": {
|
| 6 |
+
"main": "nanbeige4_2_3b_decode_int8hu_block32_sym_s1.aimodel"
|
| 7 |
+
},
|
| 8 |
+
"language": {
|
| 9 |
+
"tokenizer": "Nanbeige/Nanbeige4.2-3B",
|
| 10 |
+
"vocab_size": 166144,
|
| 11 |
+
"max_context_length": 4096,
|
| 12 |
+
"embedded_tokenizer": true,
|
| 13 |
+
"function_map": {
|
| 14 |
+
"main": [
|
| 15 |
+
"main"
|
| 16 |
+
]
|
| 17 |
+
}
|
| 18 |
+
},
|
| 19 |
+
"source": {
|
| 20 |
+
"model_definition": "torch",
|
| 21 |
+
"hf_model_id": "Nanbeige/Nanbeige4.2-3B",
|
| 22 |
+
"hf_revision": "5ff54fb7ed86ce8e216d78bff5417ab9981de3d4"
|
| 23 |
+
},
|
| 24 |
+
"compression": null,
|
| 25 |
+
"compilation": {
|
| 26 |
+
"date": "2026-07-22T15:06:28.708628+00:00",
|
| 27 |
+
"targets": []
|
| 28 |
+
}
|
| 29 |
+
}
|
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/nanbeige4_2_3b_decode_int8hu_block32_sym_s1.aimodel/main.hash
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
`Y
|
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/nanbeige4_2_3b_decode_int8hu_block32_sym_s1.aimodel/main.mlirb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60590d64a7a2808ba8db6dbf89a4dc7e2fa994485596a0c56c4cdfa972448a43
|
| 3 |
+
size 4909579220
|
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/nanbeige4_2_3b_decode_int8hu_block32_sym_s1.aimodel/metadata.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"assetVersion" : "2.0",
|
| 3 |
+
"producer" : "coreai-core 1.0.0b2",
|
| 4 |
+
"creationDate" : "20260722T150626Z"
|
| 5 |
+
}
|
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/added_tokens.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 166104,
|
| 3 |
+
"</tool_call>": 166106,
|
| 4 |
+
"<think>": 166103,
|
| 5 |
+
"<tool_call>": 166105,
|
| 6 |
+
"<|endoftext|>": 166102,
|
| 7 |
+
"<|im_end|>": 166101,
|
| 8 |
+
"<|im_start|>": 166100
|
| 9 |
+
}
|
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/chat_template.jinja
ADDED
|
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
|
| 3 |
+
{%- macro visible_text(content) -%}
|
| 4 |
+
{%- if content is string -%}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping -%}
|
| 7 |
+
{%- for item in content -%}
|
| 8 |
+
{%- if item is mapping and item.type == 'text' -%}
|
| 9 |
+
{{- item.text }}
|
| 10 |
+
{%- elif item is string -%}
|
| 11 |
+
{{- item }}
|
| 12 |
+
{%- elif item is mapping and item.type in ['image', 'image_url', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}
|
| 13 |
+
{%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%}
|
| 14 |
+
{{- "<reminder>You are unable to process this " ~ media_type ~ " because you don't have multi-modal input ability. Try different methods.</reminder>" }}
|
| 15 |
+
{%- endif -%}
|
| 16 |
+
{%- endfor -%}
|
| 17 |
+
{%- else -%}
|
| 18 |
+
{{- content }}
|
| 19 |
+
{%- endif -%}
|
| 20 |
+
{%- endmacro -%}
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
{%- set tool_call_format = tool_call_format if tool_call_format is defined else 'xml' %}
|
| 24 |
+
{%- if tools %}
|
| 25 |
+
{{- '<|im_start|>system\n' }}
|
| 26 |
+
{%- if messages|length > 0 and messages[0].get('role', '') == 'system' %}
|
| 27 |
+
{{- visible_text(messages[0].content) + '\n\n' }}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{{- '你是一位工具函数调用专家,你会得到一个问题和一组可能的工具函数。根据问题,你需要进行一个或多个函数/工具调用以实现目的,请尽量尝试探索通过工具解决问题。\n如果没有一个函数可以使用,请直接使用自然语言回复用户。\n如果给定的问题缺少函数所需的参数,请使用自然语言进行提问,向用户询问必要信息。\n如果调用结果已经足够回答用户问题,请对历史结果进行总结,使用自然语言回复用户。' }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
|
| 32 |
+
{{- "# 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>" }}
|
| 33 |
+
{%- for tool in tools %}
|
| 34 |
+
{{- "\n" }}
|
| 35 |
+
{{- tool | tojson }}
|
| 36 |
+
{%- endfor %}
|
| 37 |
+
|
| 38 |
+
{%- if tool_call_format == 'json' %}
|
| 39 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n" }}
|
| 40 |
+
{{- '<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n' }}
|
| 41 |
+
{%- else %}
|
| 42 |
+
{{- "\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n" }}
|
| 43 |
+
{{- '<tool_call>
|
| 44 |
+
<function=example_function_name>
|
| 45 |
+
<parameter=example_parameter_1>
|
| 46 |
+
value_1
|
| 47 |
+
</parameter>
|
| 48 |
+
<parameter=example_parameter_2>
|
| 49 |
+
This is the value for the second parameter
|
| 50 |
+
that can span
|
| 51 |
+
multiple lines
|
| 52 |
+
</parameter>
|
| 53 |
+
</function>
|
| 54 |
+
</tool_call><|im_end|>\n' }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
|
| 57 |
+
{%- else %}
|
| 58 |
+
{%- if messages|length > 0 and messages[0].get('role', '') == 'system' %}
|
| 59 |
+
{{- '<|im_start|>system\n' + visible_text(messages[0].content) + '<|im_end|>\n' }}
|
| 60 |
+
{%- else %}
|
| 61 |
+
{{- '<|im_start|>system\n你是南北阁,一款由BOSS直聘自主研发并训练的专业大语言模型。<|im_end|>\n' }}
|
| 62 |
+
{%- endif %}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
|
| 65 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 66 |
+
{%- for message in messages[::-1] %}
|
| 67 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 68 |
+
{%- if ns.multi_step_tool and message.get('role', '') == "user" and visible_text(message.content) is string and not(visible_text(message.content).startswith('<tool_response>') and visible_text(message.content).endswith('</tool_response>')) %}
|
| 69 |
+
{%- set ns.multi_step_tool = false %}
|
| 70 |
+
{%- set ns.last_query_index = index %}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{%- endfor %}
|
| 73 |
+
|
| 74 |
+
{%- for message in messages %}
|
| 75 |
+
{%- if visible_text(message.content) is string %}
|
| 76 |
+
{%- set content = visible_text(message.content) %}
|
| 77 |
+
{%- else %}
|
| 78 |
+
{%- set content = '' %}
|
| 79 |
+
{%- endif %}
|
| 80 |
+
|
| 81 |
+
{%- if message.get('role', '') == "system" %}
|
| 82 |
+
{%- if not loop.first %}
|
| 83 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
|
| 86 |
+
{%- elif message.get('role', '') == "assistant" %}
|
| 87 |
+
{%- set reasoning_content = '' %}
|
| 88 |
+
{%- if message.reasoning_content is string %}
|
| 89 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 90 |
+
{%- else %}
|
| 91 |
+
{%- if '</think>' in content %}
|
| 92 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 93 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 94 |
+
{%- endif %}
|
| 95 |
+
{%- endif %}
|
| 96 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 97 |
+
|
| 98 |
+
{%- if (preserve_thinking is defined and preserve_thinking is false) and (loop.index0 < ns.last_query_index) %}
|
| 99 |
+
{{- '<|im_start|>' + message.get('role', '') + '\n<think>\n\n</think>\n\n' + content }}
|
| 100 |
+
{%- else %}
|
| 101 |
+
{{- '<|im_start|>' + message.get('role', '') + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- endif %}
|
| 103 |
+
|
| 104 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 105 |
+
{%- if tool_call_format == 'json' %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 108 |
+
{{- '\n' }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if tool_call.function %}
|
| 111 |
+
{%- set tool_call = tool_call.function %}
|
| 112 |
+
{%- endif %}
|
| 113 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 114 |
+
{{- tool_call.name }}
|
| 115 |
+
{{- '", "arguments": ' }}
|
| 116 |
+
{%- if tool_call.arguments is string %}
|
| 117 |
+
{{- tool_call.arguments }}
|
| 118 |
+
{%- else %}
|
| 119 |
+
{{- tool_call.arguments | tojson }}
|
| 120 |
+
{%- endif %}
|
| 121 |
+
{{- '}\n</tool_call>' }}
|
| 122 |
+
{%- endfor %}
|
| 123 |
+
{%- else %}
|
| 124 |
+
{%- for tool_call in message.tool_calls %}
|
| 125 |
+
{%- if tool_call.function is defined %}
|
| 126 |
+
{%- set tool_call = tool_call.function %}
|
| 127 |
+
{%- endif %}
|
| 128 |
+
|
| 129 |
+
{%- if loop.first %}
|
| 130 |
+
{%- if content|trim %}
|
| 131 |
+
{{- '
|
| 132 |
+
|
| 133 |
+
<tool_call>
|
| 134 |
+
<function=' + tool_call.name + '>
|
| 135 |
+
' }}
|
| 136 |
+
{%- else %}
|
| 137 |
+
{{- '<tool_call>
|
| 138 |
+
<function=' + tool_call.name + '>
|
| 139 |
+
' }}
|
| 140 |
+
{%- endif %}
|
| 141 |
+
{%- else %}
|
| 142 |
+
{{- '
|
| 143 |
+
<tool_call>
|
| 144 |
+
<function=' + tool_call.name + '>
|
| 145 |
+
' }}
|
| 146 |
+
{%- endif %}
|
| 147 |
+
|
| 148 |
+
{%- if tool_call.arguments is defined %}
|
| 149 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 150 |
+
{{- '<parameter=' + args_name + '>
|
| 151 |
+
' }}
|
| 152 |
+
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
|
| 153 |
+
{{- args_value }}
|
| 154 |
+
{{- '
|
| 155 |
+
</parameter>
|
| 156 |
+
' }}
|
| 157 |
+
{%- endfor %}
|
| 158 |
+
{%- endif %}
|
| 159 |
+
{{- '</function>
|
| 160 |
+
</tool_call>' }}
|
| 161 |
+
{%- endfor %}
|
| 162 |
+
{%- endif %}
|
| 163 |
+
{%- endif %}
|
| 164 |
+
{{- '<|im_end|>\n' }}
|
| 165 |
+
|
| 166 |
+
{%- elif message.get('role', '') == "tool" %}
|
| 167 |
+
{%- if loop.previtem and loop.previtem.get('role', '') != "tool" %}
|
| 168 |
+
{{- '<|im_start|>user' }}
|
| 169 |
+
{%- endif %}
|
| 170 |
+
{{- '\n<tool_response>\n' }}
|
| 171 |
+
{{- content }}
|
| 172 |
+
{{- '\n</tool_response>' }}
|
| 173 |
+
{%- if loop.last or loop.nextitem.get('role', '') != "tool" %}
|
| 174 |
+
{{- '<|im_end|>\n' }}
|
| 175 |
+
{%- endif %}
|
| 176 |
+
{%- elif message.get('role', '') != '' %}
|
| 177 |
+
{{- '<|im_start|>' + message.get('role', '') + '\n' + content + '<|im_end|>' + '\n' }}
|
| 178 |
+
{%- endif %}
|
| 179 |
+
{%- endfor %}
|
| 180 |
+
|
| 181 |
+
{%- if add_generation_prompt %}
|
| 182 |
+
{{- '<|im_start|>assistant\n' }}
|
| 183 |
+
|
| 184 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 185 |
+
{{- '<think>
|
| 186 |
+
|
| 187 |
+
</think>
|
| 188 |
+
|
| 189 |
+
' }}
|
| 190 |
+
{%- else %}
|
| 191 |
+
{{- '<think>
|
| 192 |
+
' }}
|
| 193 |
+
{%- endif %}
|
| 194 |
+
|
| 195 |
+
{%- endif %}
|
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>"
|
| 4 |
+
],
|
| 5 |
+
"bos_token": {
|
| 6 |
+
"content": "<|im_start|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"eos_token": {
|
| 13 |
+
"content": "<|im_end|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"pad_token": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d858a0fc007f22af6ae18bfa1ae52d30e398aa9cd1ea06e7777176869346a3f
|
| 3 |
+
size 18450979
|
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb41d04798b714520a9b075727b0226538b7330254299062742c50ec8374bc36
|
| 3 |
+
size 2782298
|
gpu-pipelined/nanbeige4_2_3b_decode_int8hu_block32_sym_s1/tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"166100": {
|
| 31 |
+
"content": "<|im_start|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"166101": {
|
| 39 |
+
"content": "<|im_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"166102": {
|
| 47 |
+
"content": "<|endoftext|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"166103": {
|
| 55 |
+
"content": "<think>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"166104": {
|
| 63 |
+
"content": "</think>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"166105": {
|
| 71 |
+
"content": "<tool_call>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"166106": {
|
| 79 |
+
"content": "</tool_call>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
}
|
| 86 |
+
},
|
| 87 |
+
"additional_special_tokens": [
|
| 88 |
+
"<|endoftext|>"
|
| 89 |
+
],
|
| 90 |
+
"bos_token": "<|im_start|>",
|
| 91 |
+
"clean_up_tokenization_spaces": false,
|
| 92 |
+
"eos_token": "<|im_end|>",
|
| 93 |
+
"extra_special_tokens": {},
|
| 94 |
+
"legacy": false,
|
| 95 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 96 |
+
"pad_token": "<unk>",
|
| 97 |
+
"sp_model_kwargs": {},
|
| 98 |
+
"spaces_between_special_tokens": false,
|
| 99 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 100 |
+
"unk_token": "<unk>",
|
| 101 |
+
"use_default_system_prompt": false
|
| 102 |
+
}
|