arxiv:2412.13670
Mingzhe Du
Elfsong
AI & ML interests
Code Generation / Preference Alignment / Bias Mitigation
Recent Activity
updated
a dataset
11 days ago
Elfsong/CrowdEval_R
published
a dataset
11 days ago
Elfsong/CrowdEval_R
upvoted
a
paper
13 days ago
GuardReasoner: Towards Reasoning-based LLM Safeguards
Organizations
Papers
2
spaces
5
models
17
Elfsong/Phi-4-14B-Instruct-sft
Text Generation
•
Updated
•
6
Elfsong/Llama-3.1-8B-Instruct-sft
Text Generation
•
Updated
•
108
•
1
Elfsong/Phi-3.5-4B-instruct-sft
Text Generation
•
Updated
•
19
•
1
Elfsong/Llama-3.3-70B-Instruct-dpo
Text Generation
•
Updated
•
10
Elfsong/Llama-3.3-70B-Instruct-stf
Text Generation
•
Updated
•
5
Elfsong/Llama-3.1-8B-Instruct-dpo
Text Generation
•
Updated
•
11
Elfsong/mouadsfilter
Text2Text Generation
•
Updated
•
106
Elfsong/dpo
Updated
Elfsong/debias_model
Updated
Elfsong/my_awesome_model
Updated
datasets
68
Elfsong/CrowdEval_R
Updated
•
26
Elfsong/apps_generation
Updated
•
623
Elfsong/Venus_t
Viewer
•
Updated
•
2.08k
•
580
Elfsong/Venus_KTO
Viewer
•
Updated
•
631k
•
41
Elfsong/Venus_SFT
Viewer
•
Updated
•
276k
•
57
Elfsong/Venus_DPO
Viewer
•
Updated
•
127k
•
38
Elfsong/Llama-3.3-70B-Instruct-sft-response
Viewer
•
Updated
•
256
•
42
Elfsong/Llama-3.3-70B-Instruct-dpo-response
Viewer
•
Updated
•
256
•
41
Elfsong/Llama-3.3-70B-Instruct-response
Viewer
•
Updated
•
256
•
43
Elfsong/Llama-3.1-8B-Instruct-dpo-response
Viewer
•
Updated
•
256
•
45