32 23 75

Fanqi Wan

Wanfq

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

Articles 0

Article

FuseO1-Preview: System-II Reasoning Fusion of LLMs

Article

FuseChat-3.0: Preference Optimization for Implicit Model Fusion

View all Articles

Collections 8

Papers 7

models 66

datasets 33

Wanfq/gpqa

Viewer • Updated 22 days ago • 1.25k • 103

Wanfq/3_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation

Viewer • Updated Mar 28, 2024 • 21.8k • 31

Wanfq/3_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation

Preview • Updated Mar 28, 2024 • 3

Wanfq/2_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation

Viewer • Updated Mar 28, 2024 • 21.8k • 23

Wanfq/2_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation

Preview • Updated Mar 28, 2024 • 14

Wanfq/1_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation

Viewer • Updated Mar 28, 2024 • 21.7k • 17

Wanfq/1_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation

Preview • Updated Mar 28, 2024 • 7

Wanfq/0_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation

Preview • Updated Mar 28, 2024 • 18

Wanfq/0_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation

Preview • Updated Mar 28, 2024 • 54

Wanfq/KCA_data

Preview • Updated Jan 20, 2024 • 128 • 3

Fanqi Wan

AI & ML interests

Recent Activity

Organizations

Articles 0

FuseO1-Preview: System-II Reasoning Fusion of LLMs

FuseChat-3.0: Preference Optimization for Implicit Model Fusion

Collections 8

FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview

bartowski/FuseO1-DeekSeekR1-QwQ-SkyT1-32B-Preview-GGUF

FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview-GGUF

FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-Preview

Weighted-Reward Preference Optimization for Implicit Model Fusion

FuseAI/FuseChat-Llama-3.1-8B-Instruct

FuseAI/FuseChat-Llama-3.2-3B-Instruct

FuseAI/FuseChat-Llama-3.2-1B-Instruct

Papers 7

models 66

Wanfq/FuseLLM-7B

Wanfq/fusechat_v1_multi_teacher_woref_fnan_ckpt

Wanfq/fusechat_v1_nous_hermes_mixtral_teacher_fnan_ckpt

Wanfq/fusechat_v1_nous_hermes_solar_teacher_fnan_ckpt

Wanfq/fusechat_v1_multi_teacher_fnan_ckpt

Wanfq/KCA_Llama_2_13B_Refusal_Tuning

Wanfq/KCA_Llama_2_13B_Discarding_Tuning

Wanfq/KCA_Llama_2_13B_Open-Book_Tuning

Wanfq/KCA_Pythia_6.9B_Refusal_Tuning

Wanfq/KCA_Pythia_6.9B_Discarding_Tuning

datasets 33

Wanfq/gpqa

Wanfq/3_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation

Wanfq/3_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation

Wanfq/2_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation

Wanfq/2_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation

Wanfq/1_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation

Wanfq/1_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation

Wanfq/0_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation

Wanfq/0_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation

Wanfq/KCA_data

Fanqi Wan

AI & ML interests

Recent Activity

Organizations

Articles 0

FuseO1-Preview: System-II Reasoning Fusion of LLMs

FuseChat-3.0: Preference Optimization for Implicit Model Fusion

Collections 8

Papers 7

models 66 Sort: Recently updated

datasets 33 Sort: Recently updated

models 66

datasets 33