aries huang's picture

1 1

aries huang

skyai798

·

AI & ML interests

None yet

Recent Activity

new activity about 1 month ago

hlttxdy/STAR-1_DeepSeek-R1-Distill-Qwen-7B_dpo_over_refusal_mix_safep0.7_epoch2_lr1e-6_beta0.05_ftx0.2:Upload all_results.json with huggingface_hub

updated a model 2 months ago

skyai798/STAR-1_DeepSeek-R1-Distill-Llama-8B_sft-complete-dpo

published a model 2 months ago

skyai798/STAR-1_DeepSeek-R1-Distill-Llama-8B_sft-complete-dpo

View all activity

Organizations

models 16

skyai798/STAR-1_DeepSeek-R1-Distill-Llama-8B_sft-complete-dpo

Text Generation • 8B • Updated Sep 2

skyai798/qwen-dpo-r2

8B • Updated Jan 24

skyai798/llama-dpo-r2

Text Generation • 8B • Updated Jan 22

skyai798/llama-dpo-r2-new

skyai798/qwen2-dpo-r1-1v2

8B • Updated Jan 20

skyai798/qwen-dpo-r1-1v2

skyai798/qwen2_safe_40000_helpful_40000_qwen_beta_0.2_lr_1.0e-6_seed_17

skyai798/qwen2_safe_20000_helpful_40000_qwen_beta_0.2_lr_5.0e-7_seed_120

skyai798/qwen-dpo-r1-2v2

skyai798/llama-dpo-r1

Text Generation • 8B • Updated Jan 19

datasets 1

skyai798/DeceptionBench

Viewer • Updated May 16 • 150 • 30