Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
71 changes: 68 additions & 3 deletions xinference/model/llm/llm_family.json
Original file line number Diff line number Diff line change
Expand Up @@ -1485,6 +1485,71 @@
"<|endoftext|>"
]
},
{
"version": 2,
"context_length": 32768,
"model_name": "MiniCPM-V-4.5",
"model_lang": [
"en",
"zh"
],
"model_ability": [
"chat",
"vision"
],
"model_description": "MiniCPM-V 4.5 is an improved version in the MiniCPM-V series with enhanced multimodal capabilities and better performance.",
"model_specs": [
{
"model_format": "pytorch",
"model_size_in_billions": 8,
"model_src": {
"huggingface": {
"quantizations": [
"none"
],
"model_id": "openbmb/MiniCPM-V-4_5",
"model_revision": "main"
},
"modelscope": {
"quantizations": [
"none"
],
"model_id": "OpenBMB/MiniCPM-V-4_5",
"model_revision": "master"
}
}
},
{
"model_format": "pytorch",
"model_size_in_billions": 8,
"model_src": {
"huggingface": {
"quantizations": [
"none"
],
"model_id": "openbmb/MiniCPM-V-4_5-int4",
"model_revision": "main"
},
"modelscope": {
"quantizations": [
"none"
],
"model_id": "OpenBMB/MiniCPM-V-4_5-int4",
"model_revision": "master"
}
}
}
],
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|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": [
151645,
151643
],
"stop": [
"<|im_end|>",
""
]
},
{
"version": 2,
"context_length": 32768,
Expand Down Expand Up @@ -22074,8 +22139,8 @@
"4bit",
"8bit"
],
"model_id": "cpatonn/Qwen3-VL-30B-A3B-Instruct-AWQ-{quantization}"
},
"model_id": "cpatonn/Qwen3-VL-30B-A3B-Instruct-AWQ-{quantization}"
},
"modelscope": {
"quantizations": [
"4bit",
Expand Down Expand Up @@ -22218,7 +22283,7 @@
"4bit",
"8bit"
],
"model_id": "cpatonn/Qwen3-VL-30B-A3B-Thinking-AWQ-{quantization}"
"model_id": "cpatonn/Qwen3-VL-30B-A3B-Thinking-AWQ-{quantization}"
},
"modelscope": {
"quantizations": [
Expand Down
Loading
Loading