Skip to content

Commit 3fdf42b

Browse files
XprobeBotXprobeBot
authored
chore: sync models JSON [llm] (#4171)
1 parent cbedda2 commit 3fdf42b

File tree

1 file changed

+202
-0
lines changed

1 file changed

+202
-0
lines changed

‎xinference/model/llm/llm_family.json‎

Lines changed: 202 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -22085,6 +22085,208 @@
2208522085
"model_id": "cpatonn-mirror/Qwen3-VL-30B-A3B-Instruct-AWQ-{quantization}"
2208622086
}
2208722087
}
22088+
},
22089+
{
22090+
"model_format": "pytorch",
22091+
"model_size_in_billions": 32,
22092+
"model_src": {
22093+
"huggingface": {
22094+
"quantizations": [
22095+
"none"
22096+
],
22097+
"model_id": "Qwen/Qwen3-VL-32B-Instruct"
22098+
},
22099+
"modelscope": {
22100+
"quantizations": [
22101+
"none"
22102+
],
22103+
"model_id": "Qwen/Qwen3-VL-32B-Instruct"
22104+
}
22105+
}
22106+
},
22107+
{
22108+
"model_format": "fp8",
22109+
"model_size_in_billions": 32,
22110+
"model_src": {
22111+
"huggingface": {
22112+
"quantizations": [
22113+
"fp8"
22114+
],
22115+
"model_id": "Qwen/Qwen3-VL-32B-Instruct-FP8"
22116+
},
22117+
"modelscope": {
22118+
"quantizations": [
22119+
"fp8"
22120+
],
22121+
"model_id": "Qwen/Qwen3-VL-32B-Instruct-FP8"
22122+
}
22123+
}
22124+
},
22125+
{
22126+
"model_format": "awq",
22127+
"model_size_in_billions": 32,
22128+
"model_src": {
22129+
"huggingface": {
22130+
"quantizations": [
22131+
"Int4"
22132+
],
22133+
"model_id": "QuantTrio/Qwen3-VL-32B-Instruct-AWQ"
22134+
},
22135+
"modelscope": {
22136+
"quantizations": [
22137+
"Int4"
22138+
],
22139+
"model_id": "tclf90/Qwen3-VL-32B-Instruct-AWQ"
22140+
}
22141+
}
22142+
},
22143+
{
22144+
"model_format": "pytorch",
22145+
"model_size_in_billions": 8,
22146+
"model_src": {
22147+
"huggingface": {
22148+
"quantizations": [
22149+
"none"
22150+
],
22151+
"model_id": "Qwen/Qwen3-VL-8B-Instruct"
22152+
},
22153+
"modelscope": {
22154+
"quantizations": [
22155+
"none"
22156+
],
22157+
"model_id": "Qwen/Qwen3-VL-8B-Instruct"
22158+
}
22159+
}
22160+
},
22161+
{
22162+
"model_format": "fp8",
22163+
"model_size_in_billions": 8,
22164+
"model_src": {
22165+
"huggingface": {
22166+
"quantizations": [
22167+
"fp8"
22168+
],
22169+
"model_id": "Qwen/Qwen3-VL-8B-Instruct-FP8"
22170+
},
22171+
"modelscope": {
22172+
"quantizations": [
22173+
"fp8"
22174+
],
22175+
"model_id": "Qwen/Qwen3-VL-8B-Instruct-FP8"
22176+
}
22177+
}
22178+
},
22179+
{
22180+
"model_format": "awq",
22181+
"model_size_in_billions": 8,
22182+
"model_src": {
22183+
"huggingface": {
22184+
"quantizations": [
22185+
"4bit",
22186+
"8bit"
22187+
],
22188+
"model_id": "cpatonn/Qwen3-VL-8B-Instruct-AWQ-{quantization}"
22189+
},
22190+
"modelscope": {
22191+
"quantizations": [
22192+
"4bit",
22193+
"8bit"
22194+
],
22195+
"model_id": "cpatonn-mirror/Qwen3-VL-8B-Instruct-AWQ-{quantization}"
22196+
}
22197+
}
22198+
},
22199+
{
22200+
"model_format": "pytorch",
22201+
"model_size_in_billions": 4,
22202+
"model_src": {
22203+
"huggingface": {
22204+
"quantizations": [
22205+
"none"
22206+
],
22207+
"model_id": "Qwen/Qwen3-VL-4B-Instruct"
22208+
},
22209+
"modelscope": {
22210+
"quantizations": [
22211+
"none"
22212+
],
22213+
"model_id": "Qwen/Qwen3-VL-4B-Instruct"
22214+
}
22215+
}
22216+
},
22217+
{
22218+
"model_format": "fp8",
22219+
"model_size_in_billions": 4,
22220+
"model_src": {
22221+
"huggingface": {
22222+
"quantizations": [
22223+
"fp8"
22224+
],
22225+
"model_id": "Qwen/Qwen3-VL-4B-Instruct-FP8"
22226+
},
22227+
"modelscope": {
22228+
"quantizations": [
22229+
"fp8"
22230+
],
22231+
"model_id": "Qwen/Qwen3-VL-4B-Instruct-FP8"
22232+
}
22233+
}
22234+
},
22235+
{
22236+
"model_format": "awq",
22237+
"model_size_in_billions": 4,
22238+
"model_src": {
22239+
"huggingface": {
22240+
"quantizations": [
22241+
"4bit",
22242+
"8bit"
22243+
],
22244+
"model_id": "cpatonn/Qwen3-VL-4B-Instruct-AWQ-{quantization}"
22245+
},
22246+
"modelscope": {
22247+
"quantizations": [
22248+
"4bit",
22249+
"8bit"
22250+
],
22251+
"model_id": "cpatonn-mirror/Qwen3-VL-4B-Instruct-AWQ-{quantization}"
22252+
}
22253+
}
22254+
},
22255+
{
22256+
"model_format": "pytorch",
22257+
"model_size_in_billions": 2,
22258+
"model_src": {
22259+
"huggingface": {
22260+
"quantizations": [
22261+
"none"
22262+
],
22263+
"model_id": "Qwen/Qwen3-VL-2B-Instruct"
22264+
},
22265+
"modelscope": {
22266+
"quantizations": [
22267+
"none"
22268+
],
22269+
"model_id": "Qwen/Qwen3-VL-2B-Instruct"
22270+
}
22271+
}
22272+
},
22273+
{
22274+
"model_format": "fp8",
22275+
"model_size_in_billions": 2,
22276+
"model_src": {
22277+
"huggingface": {
22278+
"quantizations": [
22279+
"fp8"
22280+
],
22281+
"model_id": "Qwen/Qwen3-VL-2B-Instruct-FP8"
22282+
},
22283+
"modelscope": {
22284+
"quantizations": [
22285+
"fp8"
22286+
],
22287+
"model_id": "Qwen/Qwen3-VL-2B-Instruct-FP8"
22288+
}
22289+
}
2208822290
}
2208922291
],
2209022292
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\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' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\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",

0 commit comments

Comments
 (0)