12 1

宋小猫

SongXiaoMao

AI & ML interests

None yet

Recent Activity

new activity 7 days ago

kosbu/QVQ-72B-Preview-AWQ:Very easy to use

new activity 14 days ago

Qwen/QwQ-32B-Preview:multi GPU inferencing

new activity 14 days ago

Qwen/QwQ-32B-Preview:Use sample code to start error reporting

View all activity

Organizations

None yet

SongXiaoMao's activity

New activity in kosbu/QVQ-72B-Preview-AWQ 7 days ago

Very easy to use

#2 opened 7 days ago by

SongXiaoMao

New activity in Qwen/QwQ-32B-Preview 14 days ago

multi GPU inferencing

#18 opened about 1 month ago by

cjj2003

Use sample code to start error reporting

#45 opened 24 days ago by

SongXiaoMao

vllm reply garbled

#29 opened about 1 month ago by

SongXiaoMao

vllm has problems running this model

#46 opened 19 days ago by

SongXiaoMao

Can you officially support VLLM?

#48 opened 15 days ago by

SongXiaoMao

New activity in mistralai/Mistral-Nemo-Instruct-2407 5 months ago

Does vllm support this model yet?

#63 opened 5 months ago by

SongXiaoMao

New activity in TechxGenus/Mistral-Large-Instruct-2407-AWQ 5 months ago

The model can be started using vllm, but no dialogue is possible.

#2 opened 5 months ago by

SongXiaoMao

New activity in mistralai/Mistral-Nemo-Instruct-2407 6 months ago

How should vllm start it?

#24 opened 6 months ago by

SongXiaoMao

New activity in CohereForAI/c4ai-command-r-plus-4bit 6 months ago

请问这个4bit模型支持vllm启动吗？

#11 opened 6 months ago by

SongXiaoMao

New activity in Thireus/Vicuna13B-v1.1-8bit-128g over 1 year ago

This model can be used normally using oobabooga

#5 opened over 1 year ago by

SongXiaoMao

New activity in samwit/vicuna-13b-8bit over 1 year ago

Running on a 3090 graphics card can actually cause flash memory?

#2 opened over 1 year ago by

SongXiaoMao