xinference 0.15.0__py3-none-any.whl → 0.15.2__py3-none-any.whl

xinference/model/llm/llm_family.json

@@ -6828,6 +6828,33 @@
         ],
         "model_id":"Qwen/Qwen2-VL-2B-Instruct",
         "model_revision":"096da3b96240e3d66d35be0e5ccbe282eea8d6b1"
+      },
+         {
+        "model_format":"gptq",
+        "model_size_in_billions":2,
+        "quantizations":[
+          "Int8"
+        ],
+        "model_id":"Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8",
+        "model_revision":"d15fb11857ccc566903e2e71341f9db7babb567b"
+      },
+        {
+        "model_format":"gptq",
+        "model_size_in_billions":2,
+        "quantizations":[
+          "Int4"
+        ],
+        "model_id":"Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4",
+        "model_revision":"800d396518c82960ce6d231adecd07bbc474f0a9"
+      },
+         {
+        "model_format":"awq",
+        "model_size_in_billions":2,
+        "quantizations":[
+          "Int4"
+        ],
+        "model_id":"Qwen/Qwen2-VL-2B-Instruct-AWQ",
+        "model_revision":"ea8c5854c0044e28626719292de0d9b1a671f6fc"
       },
       {
         "model_format":"pytorch",
@@ -6837,6 +6864,173 @@
         ],
         "model_id":"Qwen/Qwen2-VL-7B-Instruct",
         "model_revision":"6010982c1010c3b222fa98afc81575f124aa9bd6"
+      },
+        {
+        "model_format":"gptq",
+        "model_size_in_billions":7,
+        "quantizations":[
+          "Int8"
+        ],
+        "model_id":"Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8",
+        "model_revision":"3d152a77eaccfd72d59baedb0b183a1b8fd56e48"
+      },
+      {
+        "model_format":"gptq",
+        "model_size_in_billions":7,
+        "quantizations":[
+          "Int4"
+        ],
+        "model_id":"Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4",
+        "model_revision":"5ab897112fa83b9699826be8753ef9184585c77d"
+      },
+      {
+        "model_format":"awq",
+        "model_size_in_billions":7,
+        "quantizations":[
+          "Int4"
+        ],
+        "model_id":"Qwen/Qwen2-VL-7B-Instruct-AWQ",
+        "model_revision":"f94216e8b513933bccd567bcd9b7350199f32538"
+      },
+      {
+        "model_format":"pytorch",
+        "model_size_in_billions":72,
+        "quantizations":[
+          "none"
+        ],
+        "model_id":"Qwen/Qwen2-VL-72B-Instruct"
+      },
+      {
+        "model_format":"awq",
+        "model_size_in_billions":72,
+        "quantizations":[
+          "Int4"
+        ],
+        "model_id":"Qwen/Qwen2-VL-72B-Instruct-AWQ"
+      },
+      {
+        "model_format":"gptq",
+        "model_size_in_billions":72,
+        "quantizations":[
+          "Int4",
+          "Int8"
+        ],
+        "model_id":"Qwen/Qwen2-VL-72B-Instruct-GPTQ-{quantization}"
+      }
+    ],
+    "prompt_style":{
+      "style_name":"QWEN",
+      "system_prompt":"You are a helpful assistant",
+      "roles":[
+        "user",
+        "assistant"
+      ],
+      "stop": [
+        "<|im_end|>",
+        "<|endoftext|>"
+      ]
+    }
+  },
+  {
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "minicpm3-4b",
+    "model_lang": [
+      "zh"
+    ],
+    "model_ability": [
+      "chat"
+    ],
+    "model_description": "MiniCPM3-4B is the 3rd generation of MiniCPM series. The overall performance of MiniCPM3-4B surpasses Phi-3.5-mini-Instruct and GPT-3.5-Turbo-0125, being comparable with many recent 7B~9B models.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 4,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "openbmb/MiniCPM3-4B",
+        "model_revision": "75f9f1097d9d66d11f37fff49210bf940455f8ac"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 4,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "openbmb/MiniCPM3-4B-GPTQ-Int4",
+        "model_revision": "97a66a62f7d09c1ee35b087b42694716a8113dce"
+      }
+    ],
+    "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+    "stop_token_ids": [
+      1,
+      2
+    ],
+    "stop": [
+      "<s>",
+      "</s>"
+    ]
+  },
+  {
+    "version":1,
+    "context_length":32768,
+    "model_name":"qwen2-audio-instruct",
+    "model_lang":[
+      "en",
+      "zh"
+    ],
+    "model_ability":[
+      "chat",
+      "audio"
+    ],
+    "model_description":"Qwen2-Audio: A large-scale audio-language model which is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions.",
+    "model_specs":[
+      {
+        "model_format":"pytorch",
+        "model_size_in_billions":7,
+        "quantizations":[
+          "none"
+        ],
+        "model_id":"Qwen/Qwen2-Audio-7B-Instruct",
+        "model_revision":"bac62d2c6808845904c709c17a0402d817558c64"
+      }
+    ],
+    "prompt_style":{
+      "style_name":"QWEN",
+      "system_prompt":"You are a helpful assistant",
+      "roles":[
+        "user",
+        "assistant"
+      ],
+      "stop": [
+        "<|im_end|>",
+        "<|endoftext|>"
+      ]
+    }
+  },
+  {
+    "version":1,
+    "context_length":32768,
+    "model_name":"qwen2-audio",
+    "model_lang":[
+      "en",
+      "zh"
+    ],
+    "model_ability":[
+      "chat",
+      "audio"
+    ],
+    "model_description":"Qwen2-Audio: A large-scale audio-language model which is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions.",
+    "model_specs":[
+      {
+        "model_format":"pytorch",
+        "model_size_in_billions":7,
+        "quantizations":[
+          "none"
+        ],
+        "model_id":"Qwen/Qwen2-Audio-7B",
+        "model_revision":"8577bc71d330c8fa32ffe9f8a1374100759f2466"
       }
     ],
     "prompt_style":{
@@ -6851,5 +7045,1052 @@
         "<|endoftext|>"
       ]
     }
+  },
+  {
+    "version": 1,
+    "context_length": 128000,
+    "model_name": "deepseek-v2",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "generate"
+    ],
+    "model_description": "DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. ",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 16,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "deepseek-ai/DeepSeek-V2-Lite",
+        "model_revision": "604d5664dddd88a0433dbae533b7fe9472482de0"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 236,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "deepseek-ai/DeepSeek-V2",
+        "model_revision": "4461458f186c35188585855f28f77af5661ad489"
+      }
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 128000,
+    "model_name": "deepseek-v2-chat",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat"
+    ],
+    "model_description": "DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. ",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 16,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "deepseek-ai/DeepSeek-V2-Lite-Chat",
+        "model_revision": "85864749cd611b4353ce1decdb286193298f64c7"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 236,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "deepseek-ai/DeepSeek-V2-Chat",
+        "model_revision": "8e3f5f6c2226787e41ba3e9283a06389d178c926"
+      }
+    ],
+    "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ '<｜begin▁of▁sentence｜>' }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + '<｜end▁of▁sentence｜>' }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+    "stop_token_ids": [
+      100001
+    ],
+    "stop": [
+      "<｜end▁of▁sentence｜>"
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 128000,
+    "model_name": "deepseek-v2-chat-0628",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat"
+    ],
+    "model_description": "DeepSeek-V2-Chat-0628 is an improved version of DeepSeek-V2-Chat. ",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 236,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "deepseek-ai/DeepSeek-V2-Chat-0628",
+        "model_revision": "5d09e272c2b223830f4e84359cd9dd047a5d7c78"
+      }
+    ],
+    "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ '<｜begin▁of▁sentence｜>' }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<｜User｜>' + message['content'] }}{% elif message['role'] == 'assistant' %}{{ '<｜Assistant｜>' + message['content'] + '<｜end▁of▁sentence｜>' }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<｜Assistant｜>' }}{% endif %}",
+    "stop_token_ids": [
+      100001
+    ],
+    "stop": [
+      "<｜end▁of▁sentence｜>"
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 128000,
+    "model_name": "deepseek-v2.5",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat"
+    ],
+    "model_description": "DeepSeek-V2.5 is an upgraded version that combines DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct. The new model integrates the general and coding abilities of the two previous versions.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 236,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "deepseek-ai/DeepSeek-V2.5",
+        "model_revision": "24b08cb750e0c2757de112d2e16327cb21ed4833"
+      }
+    ],
+    "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}    {%- if message['role'] == 'system' %}        {% set ns.system_prompt = message['content'] %}    {%- endif %}{%- endfor %}{{'<｜begin▁of▁sentence｜>'}}{{ns.system_prompt}}{%- for message in messages %}    {%- if message['role'] == 'user' %}    {%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}    {%- endif %}    {%- if message['role'] == 'assistant' and message['content'] is none %}        {%- set ns.is_tool = false -%}        {%- for tool in message['tool_calls']%}            {%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}            {%- set ns.is_first = true -%}            {%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}                   {%- endif %}        {%- endfor %}    {%- endif %}    {%- if message['role'] == 'assistant' and message['content'] is not none %}        {%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}        {%- set ns.is_tool = false -%}        {%- else %}{{'<｜Assistant｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}        {%- endif %}    {%- endif %}    {%- if message['role'] == 'tool' %}        {%- set ns.is_tool = true -%}        {%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}        {%- set ns.is_output_first = false %}        {%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}        {%- endif %}    {%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+    "stop_token_ids": [
+      100001
+    ],
+    "stop": [
+      "<｜end▁of▁sentence｜>"
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 131072,
+    "model_name": "yi-coder-chat",
+    "model_lang": [
+      "en"
+    ],
+    "model_ability": [
+      "chat"
+    ],
+    "model_description": "Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.Excelling in long-context understanding with a maximum context length of 128K tokens.Supporting 52 major programming languages, including popular ones such as Java, Python, JavaScript, and C++.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 9,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "01ai/Yi-Coder-9B-Chat",
+        "model_revision": "356a1f8d4e4a606d0b879e54191ca809918576b8"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "01ai/Yi-Coder-1.5B-Chat",
+        "model_revision": "92fdd1b2f1539ac990e7f4a921db5601da2f0299"
+      }
+    ],
+    "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+    "stop_token_ids": [
+      1,
+      2,
+      6,
+      7
+    ],
+    "stop": [
+      "<|startoftext|>",
+      "<|endoftext|>",
+      "<|im_start|>",
+      "<|im_end|>"
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 131072,
+    "model_name": "yi-coder",
+    "model_lang": [
+      "en"
+    ],
+    "model_ability": [
+      "generate"
+    ],
+    "model_description": "Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.Excelling in long-context understanding with a maximum context length of 128K tokens.Supporting 52 major programming languages, including popular ones such as Java, Python, JavaScript, and C++.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 9,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "01-ai/Yi-Coder-9B",
+        "model_revision": "e20f8087a9507ac8bce409dc5db5d0c608124238"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "01-ai/Yi-Coder-1.5B",
+        "model_revision": "00e59e64f47d3c78e4cfbdd345888479797e8109"
+      }
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "qwen2.5",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "generate"
+    ],
+    "model_description": "Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": "0_5",
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-0.5B",
+        "model_revision": "2630d3d2321bc1f1878f702166d1b2af019a7310"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-1.5B",
+        "model_revision": "e5dfabbcffd9b0c7b31d89b82c5a6b72e663f32c"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 3,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-3B",
+        "model_revision": "e4aa5ac50aa507415cda96cc99eb77ad0a3d2d34"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-7B",
+        "model_revision": "09a0bac5707b43ec44508eab308b0846320c1ed4"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 14,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-14B",
+        "model_revision": "d02b64ba1ce86bf9948668a13f82709600431ccc"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-32B",
+        "model_revision": "ff23665d01c3665be5fdb271d18a62090b65c06d"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 72,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-72B",
+        "model_revision": "587cc4061cf6a7cc0d429d05c109447e5cf063af"
+      }
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "qwen2.5-instruct",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat",
+      "tools"
+    ],
+    "model_description": "Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": "0_5",
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-0.5B-Instruct"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-1.5B-Instruct"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 3,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-3B-Instruct"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-7B-Instruct"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 14,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-14B-Instruct"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-32B-Instruct"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 72,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-72B-Instruct"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": "0_5",
+        "quantizations": [
+          "Int4",
+          "Int8"
+        ],
+        "model_id": "Qwen/Qwen2.5-0.5B-Instruct-GPTQ-{quantization}"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "Int4",
+          "Int8"
+        ],
+        "model_id": "Qwen/Qwen2.5-1.5B-Instruct-GPTQ-{quantization}"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 3,
+        "quantizations": [
+          "Int4",
+          "Int8"
+        ],
+        "model_id": "Qwen/Qwen2.5-3B-Instruct-GPTQ-{quantization}"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "Int4",
+          "Int8"
+        ],
+        "model_id": "Qwen/Qwen2.5-7B-Instruct-GPTQ-{quantization}"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 14,
+        "quantizations": [
+          "Int4",
+          "Int8"
+        ],
+        "model_id": "Qwen/Qwen2.5-14B-Instruct-GPTQ-{quantization}"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "Int4",
+          "Int8"
+        ],
+        "model_id": "Qwen/Qwen2.5-32B-Instruct-GPTQ-{quantization}"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 72,
+        "quantizations": [
+          "Int4",
+          "Int8"
+        ],
+        "model_id": "Qwen/Qwen2.5-72B-Instruct-GPTQ-{quantization}"
+      },
+      {
+        "model_format": "awq",
+        "model_size_in_billions": "0_5",
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen2.5-0.5B-Instruct-AWQ"
+      },
+      {
+        "model_format": "awq",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen2.5-1.5B-Instruct-AWQ"
+      },
+      {
+        "model_format": "awq",
+        "model_size_in_billions": 3,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen2.5-3B-Instruct-AWQ"
+      },
+      {
+        "model_format": "awq",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen2.5-7B-Instruct-AWQ"
+      },
+      {
+        "model_format": "awq",
+        "model_size_in_billions": 14,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen2.5-14B-Instruct-AWQ"
+      },
+      {
+        "model_format": "awq",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen2.5-32B-Instruct-AWQ"
+      },
+      {
+        "model_format": "awq",
+        "model_size_in_billions": 72,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "Qwen/Qwen2.5-72B-Instruct-AWQ"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": "0_5",
+        "quantizations": [
+          "q2_k",
+          "q3_k_m",
+          "q4_0",
+          "q4_k_m",
+          "q5_0",
+          "q5_k_m",
+          "q6_k",
+          "q8_0"
+        ],
+        "model_id": "Qwen/Qwen2.5-0.5B-Instruct-GGUF",
+        "model_file_name_template": "qwen2.5-0.5b-instruct-{quantization}.gguf"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "q2_k",
+          "q3_k_m",
+          "q4_0",
+          "q4_k_m",
+          "q5_0",
+          "q5_k_m",
+          "q6_k",
+          "q8_0"
+        ],
+        "model_id": "Qwen/Qwen2.5-1.5B-Instruct-GGUF",
+        "model_file_name_template": "qwen2.5-1.5b-instruct-{quantization}.gguf"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 3,
+        "quantizations": [
+          "q2_k",
+          "q3_k_m",
+          "q4_0",
+          "q4_k_m",
+          "q5_0",
+          "q5_k_m",
+          "q6_k",
+          "q8_0"
+        ],
+        "model_id": "Qwen/Qwen2.5-3B-Instruct-GGUF",
+        "model_file_name_template": "qwen2.5-3b-instruct-{quantization}.gguf"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "q2_k",
+          "q3_k_m",
+          "q4_0",
+          "q4_k_m",
+          "q5_0",
+          "q5_k_m",
+          "q6_k",
+          "q8_0"
+        ],
+        "model_id": "Qwen/Qwen2.5-7B-Instruct-GGUF",
+        "model_file_name_template": "qwen2.5-7b-instruct-{quantization}.gguf",
+        "model_file_name_split_template": "qwen2.5-7b-instruct-{quantization}-{part}.gguf",
+        "quantization_parts": {
+          "q4_0": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q4_k_m": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q5_0": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q5_k_m": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q6_k": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q8_0": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ]
+        }
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 14,
+        "quantizations": [
+          "q2_k",
+          "q3_k_m",
+          "q4_0",
+          "q4_k_m",
+          "q5_0",
+          "q5_k_m",
+          "q6_k",
+          "q8_0"
+        ],
+        "model_id": "Qwen/Qwen2.5-14B-Instruct-GGUF",
+        "model_file_name_template": "qwen2.5-14b-instruct-{quantization}.gguf",
+        "model_file_name_split_template": "qwen2.5-14b-instruct-{quantization}-{part}.gguf",
+        "quantization_parts": {
+          "q2_k": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q3_k_m": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q4_0": [
+            "00001-of-00003",
+            "00002-of-00003",
+            "00003-of-00003"
+          ],
+          "q4_k_m": [
+            "00001-of-00003",
+            "00002-of-00003",
+            "00003-of-00003"
+          ],
+          "q5_0": [
+            "00001-of-00003",
+            "00002-of-00003",
+            "00003-of-00003"
+          ],
+          "q5_k_m": [
+            "00001-of-00003",
+            "00002-of-00003",
+            "00003-of-00003"
+          ],
+          "q6_k": [
+            "00001-of-00004",
+            "00002-of-00004",
+            "00003-of-00004",
+            "00004-of-00004"
+          ],
+          "q8_0": [
+            "00001-of-00004",
+            "00002-of-00004",
+            "00003-of-00004",
+            "00004-of-00004"
+          ]
+        }
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "q2_k",
+          "q3_k_m",
+          "q4_0",
+          "q4_k_m",
+          "q5_0",
+          "q5_k_m",
+          "q6_k",
+          "q8_0"
+        ],
+        "model_id": "Qwen/Qwen2.5-32B-Instruct-GGUF",
+        "model_file_name_template": "qwen2_5-32b-instruct-{quantization}.gguf",
+        "model_file_name_split_template": "qwen2.5-32b-instruct-{quantization}-{part}.gguf",
+        "quantization_parts": {
+          "q2_k": [
+            "00001-of-00004",
+            "00002-of-00004",
+            "00003-of-00004",
+            "00004-of-00004"
+          ],
+          "q3_k_m": [
+            "00001-of-00005",
+            "00002-of-00005",
+            "00003-of-00005",
+            "00004-of-00005",
+            "00005-of-00005"
+          ],
+          "q4_0": [
+            "00001-of-00005",
+            "00002-of-00005",
+            "00003-of-00005",
+            "00004-of-00005",
+            "00005-of-00005"
+          ],
+          "q4_k_m": [
+            "00001-of-00005",
+            "00002-of-00005",
+            "00003-of-00005",
+            "00004-of-00005",
+            "00005-of-00005"
+          ],
+          "q5_0": [
+            "00001-of-00006",
+            "00002-of-00006",
+            "00003-of-00006",
+            "00004-of-00006",
+            "00005-of-00006",
+            "00006-of-00006"
+          ],
+          "q5_k_m": [
+            "00001-of-00006",
+            "00002-of-00006",
+            "00003-of-00006",
+            "00004-of-00006",
+            "00005-of-00006",
+            "00006-of-00006"
+          ],
+          "q6_k": [
+            "00001-of-00007",
+            "00002-of-00007",
+            "00003-of-00007",
+            "00004-of-00007",
+            "00005-of-00007",
+            "00006-of-00007",
+            "00007-of-00007"
+          ],
+          "q8_0": [
+            "00001-of-00009",
+            "00002-of-00009",
+            "00003-of-00009",
+            "00004-of-00009",
+            "00005-of-00009",
+            "00006-of-00009",
+            "00007-of-00009",
+            "00008-of-00009",
+            "00009-of-00009"
+          ]
+        }
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 72,
+        "quantizations": [
+          "q2_k",
+          "q3_k_m",
+          "q4_0",
+          "q4_k_m",
+          "q5_0",
+          "q5_k_m",
+          "q6_k",
+          "q8_0",
+          "fp16"
+        ],
+        "model_id": "Qwen/Qwen2.5-72B-Instruct-GGUF",
+        "model_file_name_template": "qwen2_5-72b-instruct-{quantization}.gguf",
+        "model_file_name_split_template": "qwen2.5-72b-instruct-{quantization}-{part}.gguf",
+        "quantization_parts": {
+           "q2_k": [
+            "00001-of-00007",
+            "00002-of-00007",
+            "00003-of-00007",
+            "00004-of-00007",
+            "00005-of-00007",
+            "00006-of-00007",
+            "00007-of-00007"
+          ],
+          "q3_k_m": [
+            "00001-of-00009",
+            "00002-of-00009",
+            "00003-of-00009",
+            "00004-of-00009",
+            "00005-of-00009",
+            "00006-of-00009",
+            "00007-of-00009",
+            "00008-of-00009",
+            "00009-of-00009"
+          ],
+          "q4_0": [
+            "00001-of-00011",
+            "00002-of-00011",
+            "00003-of-00011",
+            "00004-of-00011",
+            "00005-of-00011",
+            "00006-of-00011",
+            "00007-of-00011",
+            "00008-of-00011",
+            "00009-of-00011",
+            "00010-of-00011",
+            "00011-of-00011"
+          ],
+          "q4_k_m": [
+            "00001-of-00012",
+            "00002-of-00012",
+            "00003-of-00012",
+            "00004-of-00012",
+            "00005-of-00012",
+            "00006-of-00012",
+            "00007-of-00012",
+            "00008-of-00012",
+            "00009-of-00012",
+            "00010-of-00012",
+            "00011-of-00012",
+            "00012-of-00012"
+          ],
+          "q5_0": [
+            "00001-of-00013",
+            "00002-of-00013",
+            "00003-of-00013",
+            "00004-of-00013",
+            "00005-of-00013",
+            "00006-of-00013",
+            "00007-of-00013",
+            "00008-of-00013",
+            "00009-of-00013",
+            "00010-of-00013",
+            "00011-of-00013",
+            "00012-of-00013",
+            "00013-of-00013"
+          ],
+          "q5_k_m": [
+            "00001-of-00014",
+            "00002-of-00014",
+            "00003-of-00014",
+            "00004-of-00014",
+            "00005-of-00014",
+            "00006-of-00014",
+            "00007-of-00014",
+            "00008-of-00014",
+            "00009-of-00014",
+            "00010-of-00014",
+            "00011-of-00014",
+            "00012-of-00014",
+            "00013-of-00014",
+            "00014-of-00014"
+          ],
+          "q6_k": [
+            "00001-of-00016",
+            "00002-of-00016",
+            "00003-of-00016",
+            "00004-of-00016",
+            "00005-of-00016",
+            "00006-of-00016",
+            "00007-of-00016",
+            "00008-of-00016",
+            "00009-of-00016",
+            "00010-of-00016",
+            "00011-of-00016",
+            "00012-of-00016",
+            "00013-of-00016",
+            "00014-of-00016",
+            "00015-of-00016",
+            "00016-of-00016"
+          ],
+          "q8_0": [
+            "00001-of-00021",
+            "00002-of-00021",
+            "00003-of-00021",
+            "00004-of-00021",
+            "00005-of-00021",
+            "00006-of-00021",
+            "00007-of-00021",
+            "00008-of-00021",
+            "00009-of-00021",
+            "00010-of-00021",
+            "00011-of-00021",
+            "00012-of-00021",
+            "00013-of-00021",
+            "00014-of-00021",
+            "00015-of-00021",
+            "00016-of-00021",
+            "00017-of-00021",
+            "00018-of-00021",
+            "00019-of-00021",
+            "00020-of-00021",
+            "00021-of-00021"
+          ]
+        }
+      }
+    ],
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+    "stop_token_ids": [
+      151643,
+      151644,
+      151645
+    ],
+    "stop": [
+      "<|endoftext|>",
+      "<|im_start|>",
+      "<|im_end|>"
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "qwen2.5-coder",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "generate"
+    ],
+    "model_description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-Coder-1.5B",
+        "model_revision": "d3586cfe793730945f8e4d7ef31032a3ee50247d"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-Coder-7B",
+        "model_revision": "30b6a7e874a78d46b80fa1db3194ea427dd41b08"
+      }
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "qwen2.5-coder-instruct",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat",
+      "tools"
+    ],
+    "model_description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-Coder-1.5B-Instruct"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/Qwen2.5-Coder-7B-Instruct"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "q2_k",
+          "q3_k_m",
+          "q4_0",
+          "q4_k_m",
+          "q5_0",
+          "q5_k_m",
+          "q6_k",
+          "q8_0"
+        ],
+        "model_id": "Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF",
+        "model_file_name_template": "qwen2.5-coder-1.5b-instruct-{quantization}.gguf"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "q2_k",
+          "q3_k_m",
+          "q4_0",
+          "q4_k_m",
+          "q5_0",
+          "q5_k_m",
+          "q6_k",
+          "q8_0"
+        ],
+        "model_id": "Qwen/Qwen2.5-Coder-7B-Instruct-GGUF",
+        "model_file_name_template": "qwen2.5-coder-7b-instruct-{quantization}.gguf",
+        "model_file_name_split_template": "qwen2.5-coder-7b-instruct-{quantization}-{part}.gguf",
+        "quantization_parts": {
+          "q4_0": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q4_k_m": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q5_0": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q5_k_m": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q6_k": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "q8_0": [
+            "00001-of-00003",
+            "00002-of-00003",
+            "00003-of-00003"
+          ]
+        }
+      }
+    ],
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+    "stop_token_ids": [
+      151643,
+      151644,
+      151645
+    ],
+    "stop": [
+      "<|endoftext|>",
+      "<|im_start|>",
+      "<|im_end|>"
+    ]
   }
 ]