Hugging Face's logo

FuseAI

community
https://github.com/fanqiwan/FuseLLM
fanqiwan
Activity Feed

AI & ML interests

Large Language Models, Model Fusion

Recent Activity

Wanfq  new activity 2 days ago
FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview:Model Issue
Wanfq  updated a collection 3 days ago
FuseO1-Preview
Wanfq  updated a collection 3 days ago
FuseO1-Preview
View all activity

FuseAI's activity

Wanfq 
in FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview 2 days ago

Model Issue

5
#1 opened 11 days ago by
YOYO-AI
Wanfq 
updated a collection 3 days ago
Wanfq 
in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview 3 days ago

Temperature's effect on the performance of long chain reasoning models. Why was 0.7 used for the evals?

1
#6 opened 3 days ago by
j456
Wanfq 
in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview 5 days ago

DeepSeek-R1-UD-IQ1_S merge

3
#3 opened 6 days ago by
heroOfOrion

Tool use

1
#4 opened 6 days ago by
valoomba
Wanfq 
in FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview 5 days ago

Broken template for this version?

1
#2 opened 6 days ago by
pipilok
Wanfq 
in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview 7 days ago

Question about replicating the merges

2
#2 opened 7 days ago by
xi0v
Wanfq 
authored 2 papers 8 days ago
Wanfq 
updated a collection 9 days ago
Wanfq 
updated 4 models 9 days ago
Wanfq 
updated a Space 9 days ago
Wanfq 
updated 3 models 9 days ago