WPRM/judge_with_checklist_cot_new
Viewer
• Updated • 39.4k • 3
WPRM/judge_wo_checklist_cot_multimodal_filtered_8k
Viewer
• Updated • 39.8k • 5
WPRM/judge_with_checklist_cot_multimodal_filtered_8k
Viewer
• Updated • 39.3k • 4
Viewer
• Updated • 9.46k • 4
WPRM/checklist_dataset_sharegpt_for_offline_ppo_tiny
Viewer
• Updated • 8 • 4
WPRM/checklist_dataset_sharegpt_for_offline_ppo_
Viewer
• Updated • 9.46k • 4
WPRM/judge_wo_checklist_cot_multimodal_filtered_8192
Viewer
• Updated • 3
WPRM/judge_wo_checklist_cot_multimodal
Viewer
• Updated • 40.1k • 5
WPRM/judge_with_checklist_cot_multimodal
Viewer
• Updated • 39.7k • 4
Viewer
• Updated • 1.12k • 3
Viewer
• Updated • 9.46k • 3
WPRM/judge_wo_checklist_cot
Viewer
• Updated • 40.2k • 4
WPRM/judge_with_checklist_cot
Viewer
• Updated • 39.7k • 4
WPRM/preference_data_openrlhf_with_urls_len_8k_wo_checklist
Viewer
• Updated • 30.5k • 5
WPRM/preference_data_openrlhf_with_urls_len_8k
Viewer
• Updated • 30.5k • 4
WPRM/preference_data_openrlhf_with_urls
WPRM/preference_data_llama_factory_with_urls
Viewer
• Updated • 30.9k • 7
WPRM/preference_data_llama_factory_len_15k_text_with_urls
Viewer
• Updated • 30.9k • 4
WPRM/preference_data_llama_factory_len_8k_text_with_urls
Viewer
• Updated • 30.5k • 4
WPRM/preference_data_llama_factory_len_15k_text
Viewer
• Updated • 30.9k • 4
WPRM/preference_data_llama_factory_len_8k_text
Viewer
• Updated • 30.5k • 4
WPRM/preference_data_llama_factory_len_15k
Viewer
• Updated • 28k • 4
WPRM/preference_data_llama_factory_len_8k
Viewer
• Updated • 26.6k • 10
WPRM/preference_data_llama_factory_corrected_format_text_only
Viewer
• Updated • 30.9k • 3
WPRM/preference_data_llama_factory_corrected_format
Viewer
• Updated • 30.9k • 4
WPRM/preference_data_llama_factory_corrected_format_first_100
Viewer
• Updated • 100 • 4
WPRM/preference_data_llama_factory
Viewer
• Updated • 30.9k • 16
WPRM/preference_data_llama_factory_wo_checklist
Viewer
• Updated • 30.9k • 25
WPRM/mini_benchmark_webarena
Viewer
• Updated • 69 • 5
WPRM/annotated_webarena_checklist
Viewer
• Updated • 812 • 11