初始化项目，由ModelHub XC社区提供模型

Model: numind/NuExtract-2-2B-experimental Source: Original Platform
2026-05-04 22:56:44 +08:00
commit e31fbf3385
18 changed files with 4306 additions and 0 deletions
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,180 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92538": {
+      "content": "<|plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92539": {
+      "content": "<|interpreter|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92540": {
+      "content": "<|action_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92541": {
+      "content": "<|action_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92542": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92543": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92544": {
+      "content": "<img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92545": {
+      "content": "</img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92546": {
+      "content": "<IMG_CONTEXT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92547": {
+      "content": "<quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92548": {
+      "content": "</quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92549": {
+      "content": "<ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92550": {
+      "content": "</ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92551": {
+      "content": "<box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92552": {
+      "content": "</box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|action_start|>",
+    "<|action_end|>",
+    "<|interpreter|>",
+    "<|plugin|>",
+    "<img>",
+    "</img>",
+    "<IMG_CONTEXT>",
+    "<quad>",
+    "</quad>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_internlm2.InternLM2Tokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}\n    {%- if message['role'] == 'user' and template -%}\n        {{- '<|im_start|>' + message['role'] -}}\n        {{ '\n# Template:' }}\n        {{- '\n' + template }}\n        {% if examples %}\n            {{- '# Examples:' }}\n            {% for example in examples %}\n                {{- '## Input:\n' }}\n                {{- example['input'] + '\n' }}\n                {{- '## Output:\n' }}\n                {{- example['output'] | trim }}\n            {% endfor %}\n        {%- endif %}\n        {{- '# Context:' }}\n        {% if message['content'] is string %}\n            {{- message['content'] | trim }}\n        {% else %}\n            {% for content in message['content'] %}\n                {%- if content is string %}\n                    {{- content | trim }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] | trim }}\n                {%- endif %}\n            {% endfor %}\n        {% endif %}\n        {{- '<|im_end|> '}}\n    {% else %}\n        {{- '<|im_start|>' + message['role'] }}\n        {% if message['content'] is string %}\n            {{- message['content'] | trim }}\n        {% else %}\n            {% for content in message['content'] %}\n                {%- if content is string %}\n                    {{- content | trim }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] | trim }}\n                {%- endif %}\n            {% endfor %}\n        {% endif %}\n        {{- '<|im_end|> '}}\n    {% endif %}\n{% endfor -%}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant' }}\n{% endif -%}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "</s>",
+  "tokenizer_class": "InternLM2Tokenizer",
+  "unk_token": "<unk>"
+}