40 32 85

Fanqi Wan

Wanfq

https://fanqiwan.github.io/

AI & ML interests

Large Language Models, Model Fusion, Reasoning, Alignment

Recent Activity

upvoted a paper 5 days ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

liked a model 9 days ago

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

liked a model 11 days ago

deepseek-ai/DeepSeek-R1-0528

View all activity

Organizations

Wanfq's activity

New activity in Tongyi-Zhiwen/QwenLong-L1-32B 11 days ago

This model is not trained for function calling, right?

👍 1

#1 opened 13 days ago by

Anaudia

Update library_name to transformers

#4 opened 11 days ago by

sergiopaniego

commented a paper 14 days ago

QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning

Paper • 2505.17667 • Published 17 days ago • 86 •

New activity in Wanfq/Explore-LM-Ext-7B-Math 14 days ago

Adding `safetensors` variant of this model

#1 opened 16 days ago by

SFconvertbot

New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview 3 months ago

QwQ-32B

#8 opened 3 months ago by

sm54

New activity in FuseAI/FuseChat-Llama-3.1-8B-Instruct 3 months ago

Add missing metadata: library_name, pipeline_tag, license

#2 opened 3 months ago by

nielsr

commented a paper 3 months ago

FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion

Paper • 2503.04222 • Published Mar 6 • 15 •

New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview 4 months ago

what is the context lenght?

#6 opened 4 months ago by

AlgorithmicKing

New activity in FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview 4 months ago

Model Issue

🤝 1

#1 opened 5 months ago by

YOYO-AI

New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview 4 months ago

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

👍 1

#6 opened 4 months ago by

j456

New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview 4 months ago

DeepSeek-R1-UD-IQ1_S merge

#3 opened 4 months ago by

heroOfOrion

Tool use

#4 opened 4 months ago by

valoomba

New activity in FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview 4 months ago

Broken template for this version?

#2 opened 4 months ago by

pipilok

New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview 4 months ago

Question about replicating the merges

#2 opened 4 months ago by

xi0v

Flash

❤️ 3

#1 opened 5 months ago by

Mushoz

New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview 4 months ago

License of your model

🤝 1

#4 opened 5 months ago by

chewkokwah

New activity in FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview 5 months ago

Evaluation

🤝 1

#3 opened 5 months ago by

PSM24

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B 5 months ago

System Prompt

🔥 6

#3 opened 5 months ago by

Wanfq

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-14B 5 months ago

System Prompt

#2 opened 5 months ago by

Wanfq

New activity in deepseek-ai/DeepSeek-R1-Distill-Qwen-32B 5 months ago

System Prompt

👍 👀 16

#2 opened 5 months ago by

Wanfq