xinference 1.0.1__py3-none-any.whl → 1.2.1__py3-none-any.whl

xinference/model/llm/llm_family_modelscope.json

@@ -454,6 +454,72 @@
       }
     ]
   },
+  {
+    "version": 1,
+    "context_length": 131072,
+    "model_name": "llama-3.3-instruct",
+    "model_lang": [
+      "en",
+      "de",
+      "fr",
+      "it",
+      "pt",
+      "hi",
+      "es",
+      "th"
+    ],
+    "model_ability": [
+      "chat",
+      "tools"
+    ],
+    "model_description": "The Llama 3.3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks..",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 70,
+        "quantizations": [
+          "none"
+        ],
+        "model_id": "LLM-Research/Llama-3.3-70B-Instruct",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 70,
+        "quantizations": [
+          "Q3_K_L",
+          "Q4_K_M",
+          "Q6_K",
+          "Q8_0"
+        ],
+        "quantization_parts": {
+          "Q6_K": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ],
+          "Q8_0": [
+            "00001-of-00002",
+            "00002-of-00002"
+          ]
+        },
+        "model_id": "lmstudio-community/Llama-3.3-70B-Instruct-GGUF",
+        "model_file_name_template": "Llama-3.3-70B-Instruct-{quantization}.gguf",
+        "model_file_name_split_template": "Llama-3.3-70B-Instruct-{quantization}-{part}.gguf",
+        "model_hub": "modelscope"
+      }
+    ],
+    "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+    "stop_token_ids": [
+      128001,
+      128008,
+      128009
+    ],
+    "stop": [
+      "<|end_of_text|>",
+      "<|eot_id|>",
+      "<|eom_id|>"
+    ]
+  },
   {
     "version": 1,
     "context_length": 2048,
@@ -586,7 +652,7 @@
           "none"
         ],
         "model_hub": "modelscope",
-        "model_id": "ZhipuAI/glm-4-9b-chat",
+        "model_id": "ZhipuAI/glm-4-9b-chat-hf",
         "model_revision": "master"
       },
       {
@@ -652,7 +718,7 @@
           "none"
         ],
         "model_hub": "modelscope",
-        "model_id": "ZhipuAI/glm-4-9b-chat-1m",
+        "model_id": "ZhipuAI/glm-4-9b-chat-1m-hf",
         "model_revision": "master"
       },
       {
@@ -2837,7 +2903,7 @@
         "model_format": "mlx",
         "model_size_in_billions": "0_5",
         "quantizations": [
-          "4-bit"
+          "4bit"
         ],
         "model_id": "qwen/Qwen2-0.5B-Instruct-MLX",
         "model_hub": "modelscope"
@@ -2846,7 +2912,7 @@
         "model_format": "mlx",
         "model_size_in_billions": "1_5",
         "quantizations": [
-          "4-bit"
+          "4bit"
         ],
         "model_id": "qwen/Qwen2-1.5B-Instruct-MLX",
         "model_hub": "modelscope"
@@ -2855,7 +2921,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 7,
         "quantizations": [
-          "4-bit"
+          "4bit"
         ],
         "model_id": "qwen/Qwen2-7B-Instruct-MLX",
         "model_hub": "modelscope"
@@ -4649,6 +4715,16 @@
         "model_id":"qwen/Qwen2-VL-7B-Instruct-AWQ",
         "model_revision":"master"
       },
+      {
+        "model_format":"mlx",
+        "model_size_in_billions":7,
+        "quantizations":[
+          "8bit"
+        ],
+        "model_hub": "modelscope",
+        "model_id":"okwinds/Qwen2-VL-7B-Instruct-MLX-8bit",
+        "model_revision":"master"
+      },
       {
         "model_format":"pytorch",
         "model_size_in_billions":2,
@@ -4689,6 +4765,16 @@
         "model_id":"qwen/Qwen2-VL-2B-Instruct-AWQ",
         "model_revision":"master"
       },
+      {
+        "model_format":"mlx",
+        "model_size_in_billions":2,
+        "quantizations":[
+          "8bit"
+        ],
+        "model_hub": "modelscope",
+        "model_id":"okwinds/Qwen2-VL-2B-Instruct-MLX-8bit",
+        "model_revision":"master"
+      },
       {
         "model_format":"pytorch",
         "model_size_in_billions":72,
@@ -4716,6 +4802,17 @@
         ],
         "model_id":"qwen/Qwen2-VL-72B-Instruct-GPTQ-{quantization}",
         "model_hub": "modelscope"
+      },
+      {
+        "model_format":"mlx",
+        "model_size_in_billions":72,
+        "quantizations":[
+          "4bit",
+          "8bit"
+        ],
+        "model_hub": "modelscope",
+        "model_id":"okwinds/Qwen2-VL-72B-Instruct-MLX-{quantization}",
+        "model_revision":"master"
       }
     ],
     "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
@@ -5777,7 +5874,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 3,
         "quantizations": [
-          "4-bit"
+          "4bit"
         ],
         "model_id": "okwinds/Qwen2.5-3B-Instruct-MLX-4bit",
         "model_hub": "modelscope"
@@ -5786,7 +5883,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 3,
         "quantizations": [
-          "8-bit"
+          "8bit"
         ],
         "model_id": "okwinds/Qwen2.5-3B-Instruct-MLX-8bit",
         "model_hub": "modelscope"
@@ -5795,7 +5892,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 7,
         "quantizations": [
-          "4-bit"
+          "4bit"
         ],
         "model_id": "okwinds/Qwen2.5-7B-Instruct-MLX-4bit",
         "model_hub": "modelscope"
@@ -5804,7 +5901,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 7,
         "quantizations": [
-          "8-bit"
+          "8bit"
         ],
         "model_id": "okwinds/Qwen2.5-7B-Instruct-MLX-8bit",
         "model_hub": "modelscope"
@@ -5813,7 +5910,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 14,
         "quantizations": [
-          "4-bit"
+          "4bit"
         ],
         "model_id": "okwinds/Qwen2.5-14B-Instruct-MLX-4bit",
         "model_hub": "modelscope"
@@ -5822,7 +5919,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 14,
         "quantizations": [
-          "8-bit"
+          "8bit"
         ],
         "model_id": "okwinds/Qwen2.5-14B-Instruct-MLX-8bit",
         "model_hub": "modelscope"
@@ -5831,7 +5928,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 32,
         "quantizations": [
-          "2-bit"
+          "2bit"
         ],
         "model_id": "okwinds/Qwen2.5-32B-Instruct-MLX-2bit",
         "model_hub": "modelscope"
@@ -5840,7 +5937,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 32,
         "quantizations": [
-          "4-bit"
+          "4bit"
         ],
         "model_id": "okwinds/Qwen2.5-32B-Instruct-MLX-4bit",
         "model_hub": "modelscope"
@@ -5849,7 +5946,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 32,
         "quantizations": [
-          "8-bit"
+          "8bit"
         ],
         "model_id": "okwinds/Qwen2.5-32B-Instruct-MLX-8bit",
         "model_hub": "modelscope"
@@ -5858,7 +5955,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 72,
         "quantizations": [
-          "2-bit"
+          "2bit"
         ],
         "model_id": "okwinds/Qwen2.5-32B-Instruct-MLX-2bit",
         "model_hub": "modelscope"
@@ -5867,7 +5964,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 72,
         "quantizations": [
-          "4-bit"
+          "4bit"
         ],
         "model_id": "okwinds/Qwen2.5-72B-Instruct-MLX-4bit",
         "model_hub": "modelscope"
@@ -5876,7 +5973,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 72,
         "quantizations": [
-          "8-bit"
+          "8bit"
         ],
         "model_id": "okwinds/Qwen2.5-72B-Instruct-MLX-8bit",
         "model_hub": "modelscope"
@@ -6296,7 +6393,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 32,
         "quantizations": [
-          "4-bit"
+          "4bit"
         ],
         "model_id": "okwinds/QwQ-32B-Preview-MLX-4bit",
         "model_hub": "modelscope"
@@ -6305,7 +6402,7 @@
         "model_format": "mlx",
         "model_size_in_billions": 32,
         "quantizations": [
-          "8-bit"
+          "8bit"
         ],
         "model_id": "okwinds/QwQ-32B-Preview-MLX-8bit",
         "model_hub": "modelscope"
@@ -6320,7 +6417,8 @@
           "Q8_0"
         ],
         "model_id": "AI-ModelScope/QwQ-32B-Preview-GGUF",
-        "model_file_name_template": "QwQ-32B-Preview-{quantization}.gguf"
+        "model_file_name_template": "QwQ-32B-Preview-{quantization}.gguf",
+	"model_hub": "modelscope"
       }
     ],
     "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",
@@ -6335,6 +6433,194 @@
       "<|im_end|>"
     ]
   },
+  {
+    "version": 1,
+    "context_length": 131072,
+    "model_name": "deepseek-r1-distill-qwen",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat"
+    ],
+    "model_description": "deepseek-r1-distill-qwen is distilled from DeepSeek-R1 based on Qwen",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": "1_5",
+        "quantizations": [
+          "Q2_K",
+          "Q2_K_L",
+          "Q3_K_M",
+          "Q4_K_M",
+          "Q5_K_M",
+          "Q6_K",
+          "Q8_0"
+        ],
+        "model_id": "unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF",
+        "model_file_name_template": "DeepSeek-R1-Distill-Qwen-1.5B-{quantization}.gguf",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "tclf90/deepseek-r1-distill-qwen-7b-gptq-int4",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "Q2_K",
+          "Q2_K_L",
+          "Q3_K_M",
+          "Q4_K_M",
+          "Q5_K_M",
+          "Q6_K",
+          "Q8_0",
+          "F16"
+        ],
+        "model_id": "unsloth/DeepSeek-R1-Distill-Qwen-7B-GGUF",
+        "model_file_name_template": "DeepSeek-R1-Distill-Qwen-7B-{quantization}.gguf",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "3bit",
+          "4bit",
+          "6bit",
+          "8bit"
+        ],
+        "model_id": "okwinds/DeepSeek-R1-Distill-Qwen-7B-MLX-{quantization}",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 14,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 14,
+        "quantizations": [
+          "Q2_K",
+          "Q2_K_L",
+          "Q3_K_M",
+          "Q4_K_M",
+          "Q5_K_M",
+          "Q6_K",
+          "Q8_0",
+          "F16"
+        ],
+        "model_id": "unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF",
+        "model_file_name_template": "DeepSeek-R1-Distill-Qwen-14B-{quantization}.gguf",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 14,
+        "quantizations": [
+          "3bit",
+          "4bit",
+          "6bit",
+          "8bit"
+        ],
+        "model_id": "okwinds/DeepSeek-R1-Distill-Qwen-14B-MLX-{quantization}",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "gptq",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "Int4"
+        ],
+        "model_id": "tclf90/deepseek-r1-distill-qwen-32b-gptq-int4",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "Q2_K",
+          "Q2_K_L",
+          "Q3_K_M",
+          "Q4_K_M",
+          "Q5_K_M",
+          "Q6_K",
+          "Q8_0",
+          "F16"
+        ],
+        "model_id": "unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF",
+        "model_file_name_template": "DeepSeek-R1-Distill-Qwen-32B-{quantization}.gguf",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 32,
+        "quantizations": [
+          "2bit",
+          "3bit",
+          "4bit",
+          "6bit",
+          "8bit"
+        ],
+        "model_id": "okwinds/DeepSeek-R1-Distill-Qwen-32B-MLX-{quantization}",
+        "model_hub": "modelscope"
+      }
+    ],
+    "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 %}{{bos_token}}{{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 %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + 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": [
+      151643
+    ],
+    "stop": [
+      "<｜end▁of▁sentence｜>"
+    ]
+  },
   {
     "version": 1,
     "context_length": 8192,
@@ -6575,5 +6861,153 @@
       "<|user|>",
       "<|observation|>"
     ]
+  },
+  {
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "QvQ-72B-Preview",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat",
+      "vision"
+    ],
+    "model_description": "QVQ-72B-Preview is an experimental research model developed by the Qwen team, focusing on enhancing visual reasoning capabilities.",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 72,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "Qwen/QVQ-72B-Preview",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "mlx",
+        "model_size_in_billions": 72,
+        "quantizations": [
+          "3bit",
+          "4bit",
+          "6bit",
+          "8bit",
+          "bf16"
+        ],
+        "model_id": "mlx-community/QVQ-72B-Preview-{quantization}",
+        "model_hub": "modelscope"
+      }
+    ],
+    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+    "stop_token_ids": [
+      151645,
+      151643
+    ],
+    "stop": [
+      "<|im_end|>",
+      "<|endoftext|>"
+    ]
+  },
+   {
+    "version": 1,
+    "context_length": 32768,
+    "model_name": "marco-o1",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat",
+      "tools"
+    ],
+    "model_description": "Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "AIDC-AI/Marco-o1",
+        "model_hub": "modelscope"
+      },
+      {
+        "model_format": "ggufv2",
+        "model_size_in_billions": 7,
+        "quantizations": [
+          "Q2_K",
+          "Q3_K_L",
+          "Q3_K_M",
+          "Q3_K_S",
+          "Q4_0",
+          "Q4_1",
+          "Q4_K_M",
+          "Q4_K_S",
+          "Q5_0",
+          "Q5_1",
+          "Q5_K_M",
+          "Q5_K_S",
+          "Q6_K",
+          "Q8_0"
+        ],
+        "model_file_name_template": "Marco-o1.{quantization}.gguf",
+        "model_hub": "modelscope",
+        "model_id": "QuantFactory/Marco-o1-GGUF"
+      }
+    ],
+    "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\n\n你是一个经过良好训练的AI助手，你的名字是Marco-o1.由阿里国际数字商业集团的AI Business创造.\n        \n## 重要！！！！！\n当你回答问题时，你的思考应该在<Thought>内完成，<Output>内输出你的结果。\n<Thought>应该尽可能是英文，但是有2个特例，一个是对原文中的引用，另一个是是数学应该使用markdown格式，<Output>内的输出需要遵循用户输入的语言。\n        <|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+    "stop_token_ids": [
+      151643,
+      151644,
+      151645
+    ],
+    "stop": [
+      "<|endoftext|>",
+      "<|im_start|>",
+      "<|im_end|>"
+    ]
+  },
+  {
+    "version": 1,
+    "context_length": 4096,
+    "model_name": "cogagent",
+    "model_lang": [
+      "en",
+      "zh"
+    ],
+    "model_ability": [
+      "chat",
+      "vision"
+    ],
+    "model_description": "The CogAgent-9B-20241220 model is based on GLM-4V-9B, a bilingual open-source VLM base model. Through data collection and optimization, multi-stage training, and strategy improvements, CogAgent-9B-20241220 achieves significant advancements in GUI perception, inference prediction accuracy, action space completeness, and task generalizability. ",
+    "model_specs": [
+      {
+        "model_format": "pytorch",
+        "model_size_in_billions": "9",
+        "quantizations": [
+          "4-bit",
+          "8-bit",
+          "none"
+        ],
+        "model_id": "ZhipuAI/cogagent-9b-20241220",
+        "model_hub": "modelscope"
+      }
+    ],
+    "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": [
+      151329,
+      151336,
+      151338
+    ],
+    "stop": [
+      "<|endoftext|>",
+      "<|user|>",
+      "<|observation|>"
+    ]
   }
 ]

xinference/model/llm/memory.py

@@ -14,7 +14,7 @@
 
 # NOTE:
 #
-#   The algorithum is ported from https://github.com/RahulSChand/gpu_poor
+#   The algorithm is ported from https://github.com/RahulSChand/gpu_poor
 #
 #   Improvement:
 #