Dahoas/hh_prompted_human_eval
Viewer
•
Updated
•
100
•
8
Alex Havrilla
Dahoas
AI & ML interests
NLP, RL
Organizations
Dahoas
's datasets
148
Dahoas/rm-static
Viewer
•
Updated
•
81.4k
•
2.77k
•
122
Dahoas/static-hh
Viewer
•
Updated
•
101k
•
300
•
21
Dahoas/hh_human_eval
Viewer
•
Updated
•
100
•
8
Dahoas/sft_instruct_helpful_preferences
Viewer
•
Updated
•
20k
•
35
•
1
Dahoas/rm_instruct_helpful_preferences
Viewer
•
Updated
•
90.7k
•
36
•
4
Dahoas/instruct_helpful_preferences
Viewer
•
Updated
•
111k
•
19
•
1
Dahoas/instruct_preference_queries
Viewer
•
Updated
•
111k
•
8
Dahoas/filtered-SHP
Viewer
•
Updated
•
101k
•
12
•
2
Dahoas/augmented_synthetic_prompt_responses
Viewer
•
Updated
•
111k
•
15
•
3
Dahoas/full-hh-rlhf
Viewer
•
Updated
•
125k
•
1.33k
•
82
Dahoas/6B_summarization_sft_ilql_comparison
Viewer
•
Updated
•
92
•
9
Dahoas/1B_summarization_sft_ilql_comparison
Viewer
•
Updated
•
92
•
9
Dahoas/125M_summarization_sft_ilql_comparison
Viewer
•
Updated
•
92
•
10
Dahoas/pythia_125M_sft_summarize_eval_human
Viewer
•
Updated
•
100
•
10
Dahoas/pythia_6B_sft_summarize_eval_human
Viewer
•
Updated
•
100
•
8
Dahoas/pythia_1B_sft_summarize_eval_human
Viewer
•
Updated
•
100
•
9
Dahoas/ilql_20B_summarization_eval
Viewer
•
Updated
•
100
•
7
Dahoas/ilql_6B_summarization_eval
Viewer
•
Updated
•
100
•
8
Dahoas/ilql_1B_summarization_eval
Viewer
•
Updated
•
100
•
8
Dahoas/ilql_125M_summarization_eval
Viewer
•
Updated
•
100
•
8
Dahoas/20B_hh_sft_ilql_comparison
Viewer
•
Updated
•
100
•
11
Dahoas/6B_hh_sft_ilql_comparison
Viewer
•
Updated
•
100
•
10
Dahoas/1B_hh_sft_ilql_comparison
Viewer
•
Updated
•
100
•
10
Dahoas/125M_hh_sft_ilql_comparison
Viewer
•
Updated
•
100
•
7
Dahoas/ilql_20B_hh_eval
Viewer
•
Updated
•
100
•
9
Dahoas/ilql_6B_hh_eval
Viewer
•
Updated
•
100
•
9
Dahoas/ilql_1B_hh_eval
Viewer
•
Updated
•
100
•
8
Dahoas/ilql_125M_hh_eval
Viewer
•
Updated
•
100
•
10
Dahoas/6B_hh_sft_prompted_comparison
Viewer
•
Updated
•
100
•
7