Hugging Face's logo
Fanqi Wan's picture
32 23 75

Fanqi Wan

Wanfq
21world's profile picture ubergarm's profile picture eramax's profile picture
·
https://fanqiwan.github.io/

AI & ML interests

Large Language Models, Model Fusion, Self-Improving, Instruction-Tuning, Hallucination Mitigation, Dialogue Systems

Recent Activity

upvoted a collection 4 days ago
🧠 Reasoning datasets
new activity 5 days ago
FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview:Model Issue
updated a collection 6 days ago
FuseO1-Preview
View all activity

Organizations

FuseAI's profile picture Sun Yat-Sen University's profile picture DataComp 's profile picture

Wanfq's activity

upvoted a collection 4 days ago
New activity in FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview 5 days ago

Model Issue

5
#1 opened 14 days ago by
YOYO-AI
updated a collection 6 days ago
liked a model 6 days ago
New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview 6 days ago

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

1
#6 opened 6 days ago by
j456
New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview 8 days ago

DeepSeek-R1-UD-IQ1_S merge

3
#3 opened 9 days ago by
heroOfOrion

Tool use

1
#4 opened 9 days ago by
valoomba
New activity in FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview 8 days ago

Broken template for this version?

1
#2 opened 9 days ago by
pipilok
New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview 10 days ago

Question about replicating the merges

2
#2 opened 10 days ago by
xi0v
authored 2 papers 11 days ago
updated a collection 12 days ago
updated 4 models 12 days ago
updated a Space 12 days ago
updated a model 12 days ago