·
AI & ML interests
None yet
Organizations
models
48
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_gpg_sig_r_js2_kl_false
Updated
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_gpg_sig_r_js1_kl_false
Updated
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_ccpo_bce_beta0.05_sig_3_r_js2
Updated
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_ccpo_bce_beta0.05_sig_3_r_js1
Updated
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_ccpo_bce_beta0.05_beta_clip_sig_3_r_js2
Updated
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_ccpo_bce_beta0.05_beta_clip_sig_3_r_js1
Updated
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_ccpo_bce_beta0.03_beta_clip_sig_3_r_js4_kl_false
Updated
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_ccpo_bce_beta0.03_beta_clip_sig_3_r_js3_kl_false
Updated
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_ccpo_bce_beta0.03_beta_clip_sig_3_r_js2_kl_false
Updated
happyfighting/Qwen2.5-3B-Instruct-kklogic_grpo_baseline_53_ccpo_bce_beta0.03_beta_clip_sig_3_r_js1_kl_false
Updated