Hugging Face's logo
宋小猫's picture
22 1

宋小猫

SongXiaoMao
·

AI & ML interests

None yet

Recent Activity

new activity 4 days ago
Qwen/QwQ-32B:When will you fix the model replies missing</think>\n start tags
new activity 4 days ago
Qwen/QwQ-32B:When answering questions in Chinese, the model frequently terminates prematurely (outputs the end token). Is this a common problem?
new activity 5 days ago
Qwen/QwQ-32B:missing opening <think>
View all activity

Organizations

None yet

SongXiaoMao's activity

New activity in Qwen/QwQ-32B 4 days ago

When will you fix the model replies missing</think>\n start tags

17
#19 opened 8 days ago by
xldistance

When answering questions in Chinese, the model frequently terminates prematurely (outputs the end token). Is this a common problem?

1
#40 opened 7 days ago by
zhangw355
New activity in Qwen/QwQ-32B 5 days ago

missing opening <think>

18
#4 opened 8 days ago by
getfit
New activity in Valdemardi/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview-AWQ 11 days ago

非常感谢您的量化 求一个其他的量化模型可以吗？
#1 opened 11 days ago by
SongXiaoMao
New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview 13 days ago

非常喜欢这个模型
#9 opened 13 days ago by
SongXiaoMao
New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview 13 days ago

这个模型真的太好用了
#7 opened 13 days ago by
SongXiaoMao
New activity in Valdemardi/DeepSeek-R1-Distill-Llama-70B-AWQ 15 days ago

AWQ q6

1
#1 opened about 2 months ago by
D-r-e
New activity in unsloth/DeepSeek-R1-GGUF 26 days ago

I tested dynamic 1.58bit and 2.22bit, All thoughts are empty?

9
#24 opened about 1 month ago by
SongXiaoMao
New activity in unsloth/DeepSeek-R1-GGUF about 1 month ago

No think tokens visible

6
#15 opened about 1 month ago by
sudkamath
New activity in PowerInfer/SmallThinker-3B-Preview about 2 months ago

How to Pair with Larger Models

4
#7 opened 2 months ago by
windkkk
New activity in kosbu/QVQ-72B-Preview-AWQ 3 months ago

Very easy to use
#2 opened 3 months ago by
SongXiaoMao
New activity in Qwen/QwQ-32B-Preview 3 months ago

multi GPU inferencing

2
#18 opened 3 months ago by
cjj2003

Use sample code to start error reporting

1
#45 opened 3 months ago by
SongXiaoMao

vllm reply garbled

3
#29 opened 3 months ago by
SongXiaoMao

vllm has problems running this model

3
#46 opened 3 months ago by
SongXiaoMao

Can you officially support VLLM?

1
#48 opened 3 months ago by
SongXiaoMao
New activity in mistralai/Mistral-Nemo-Instruct-2407 7 months ago

Does vllm support this model yet?
#63 opened 7 months ago by
SongXiaoMao
New activity in TechxGenus/Mistral-Large-Instruct-2407-AWQ 8 months ago

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

3
#2 opened 8 months ago by
SongXiaoMao
New activity in mistralai/Mistral-Nemo-Instruct-2407 8 months ago

How should vllm start it?

2
#24 opened 8 months ago by
SongXiaoMao
updated a model 8 months ago