august66/hh_qwen1.5_IS_KL
2B • Updated
• 24
s
august66
AI & ML interests
None yet
Recent Activity
updated
a model 3 days ago
august66/hh_qwen1.5_IS_KL updated
a dataset 3 days ago
august66/hh_helpfulness_qwen2.5_1.5b_generation updated
a dataset 3 days ago
august66/hh_helpfulness_mc_rewards Organizations
models 13
august66/hh_qwen1.5_IS_CLIP_round_2
2B • Updated
• 17
august66/hh_qwen1.5_drpo_fixed_beta
2B • Updated
• 31
august66/hh_qwen1.5_IS_CLIP
2B • Updated
• 34
august66/hh_qwen1.5_drpo_adaptive_beta
Updated
august66/hh_qwen1.5_is_clip_1000_5e6
2B • Updated
• 22
august66/hh_qwen_1.5b_sft_dpo_model
2B • Updated
• 76
august66/hh_qwen1.5_drpo_target_3.0_1000_checkpoint
2B • Updated
• 12
august66/qwen2.5-1.5b-base-hh-helpful-sft
Text Generation • 2B • Updated
• 348
august66/Qwen2.5-1.5B-Instruct-reward-hh-helpful
Text Classification • 2B • Updated
• 14
datasets 34
august66/hh_helpfulness_qwen2.5_1.5b_generation
Viewer
• Updated
• 46.1k • 40
august66/hh_helpfulness_mc_rewards
Viewer
• Updated
• 46.1k • 12
august66/hh_helpfulness_drpo_from_sft
Viewer
• Updated
• 46.1k • 421
august66/hh_helpful_base
Viewer
• Updated
• 46.1k • 208
august66/hh_harmless_base
Viewer
• Updated
• 44.8k • 16
august66/drpo_hh_qwen2.5_1.5b_with_ref_prob_vllm_conv
Viewer
• Updated
• 43.8k • 37
august66/drpo_hh_qwen2.5_1.5b_with_ref_prob_vllm
Viewer
• Updated
• 43.8k • 13
august66/drpo_hh_qwen2.5_1.5b_with_ref_prob_sampled
Viewer
• Updated
• 48.8k • 96
august66/drpo_hh_qwen2.5_1.5b_with_ref_btpref
Viewer
• Updated
• 48.8k • 197
august66/hh_qwen2.5_1.5b_with_bias_bt_pref
Viewer
• Updated
• 18k • 4