Article
22
Fanqi Wan
Wanfq
AI & ML interests
Large Language Models, Model Fusion, Reasoning, Alignment
Recent Activity
liked
a model
20 days ago
deepseek-ai/DeepSeek-V3.1-Base
upvoted
a
paper
25 days ago
NextStep-1: Toward Autoregressive Image Generation with Continuous
Tokens at Scale
upvoted
a
collection
about 1 month ago
Step3
Organizations
Articles 2
Article
5
FuseChat-3.0: Preference Optimization for Implicit Model Fusion
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
-
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
Paper • 2505.17667 • Published • 89 -
Tongyi-Zhiwen/QwenLong-L1-32B
Text Generation • 33B • Updated • 1.6k • • 158 -
mradermacher/QwenLong-L1-32B-GGUF
33B • Updated • 188 • 7 -
Tongyi-Zhiwen/QwenLong-L1-32B-AWQ
6B • Updated • 445 • 10
System-II Reasoning Fusion of LLMs
-
FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview
33B • Updated • 14 • 130 -
FuseAI/FuseO1-QwQ-DeepSeekR1-LightR1-32B
33B • Updated • 6 • 13 -
bartowski/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview-GGUF
Text Generation • 33B • Updated • 263 • 44 -
FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview-GGUF
33B • Updated • 94 • 17
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
-
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
Paper • 2505.17667 • Published • 89 -
Tongyi-Zhiwen/QwenLong-L1-32B
Text Generation • 33B • Updated • 1.6k • • 158 -
mradermacher/QwenLong-L1-32B-GGUF
33B • Updated • 188 • 7 -
Tongyi-Zhiwen/QwenLong-L1-32B-AWQ
6B • Updated • 445 • 10
System-II Reasoning Fusion of LLMs
-
FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview
33B • Updated • 14 • 130 -
FuseAI/FuseO1-QwQ-DeepSeekR1-LightR1-32B
33B • Updated • 6 • 13 -
bartowski/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview-GGUF
Text Generation • 33B • Updated • 263 • 44 -
FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview-GGUF
33B • Updated • 94 • 17
models
66
Wanfq/Explore-LM-Ext-7B-Math
Text Generation
•
7B
•
Updated
•
13
Wanfq/FuseLLM-7B
Text Generation
•
7B
•
Updated
•
20
•
22
Wanfq/fusechat_v1_multi_teacher_woref_fnan_ckpt
Text Generation
•
7B
•
Updated
•
8
Wanfq/fusechat_v1_nous_hermes_mixtral_teacher_fnan_ckpt
Text Generation
•
7B
•
Updated
•
7
Wanfq/fusechat_v1_nous_hermes_solar_teacher_fnan_ckpt
Text Generation
•
7B
•
Updated
•
8
Wanfq/fusechat_v1_multi_teacher_fnan_ckpt
Text Generation
•
7B
•
Updated
•
7
Wanfq/KCA_Llama_2_13B_Refusal_Tuning
Text Generation
•
Updated
•
8
Wanfq/KCA_Llama_2_13B_Discarding_Tuning
Text Generation
•
Updated
•
8
Wanfq/KCA_Llama_2_13B_Open-Book_Tuning
Text Generation
•
Updated
•
8
Wanfq/KCA_Pythia_6.9B_Refusal_Tuning
Text Generation
•
7B
•
Updated
•
7
datasets
33
Wanfq/gpqa
Viewer
•
Updated
•
1.25k
•
264
Wanfq/3_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation
Viewer
•
Updated
•
21.8k
•
24
Wanfq/3_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation
Preview
•
Updated
Wanfq/2_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation
Viewer
•
Updated
•
21.8k
•
27
Wanfq/2_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation
Preview
•
Updated
•
3
Wanfq/1_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation
Viewer
•
Updated
•
21.7k
•
44
Wanfq/1_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation
Preview
•
Updated
•
4
Wanfq/0_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representation
Preview
•
Updated
•
57
Wanfq/0_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation
Preview
•
Updated
•
24
Wanfq/KCA_data
Preview
•
Updated
•
34
•
3