Article
Distribution Matching Prevents Mode Collapse in Training Reasoning Models
•
2
Germán Kruszewski
germank
AI & ML interests
None yet
Recent Activity
upvoted an article 4 days ago
Distribution Matching Prevents Mode Collapse in Training Reasoning Models published an article 5 days ago
Distribution Matching Prevents Mode Collapse in Training Reasoning Models updated a dataset 12 days ago
germank/alinia-test-oodOrganizations
upvoted an article 4 days ago
published an article 5 days ago
Article
Distribution Matching Prevents Mode Collapse in Training Reasoning Models
•
2
updated 2
datasets 12 days ago
updated a
dataset 17 days ago
published 2
datasets 17 days ago
published a
dataset 18 days ago
updated a
dataset 18 days ago
published a
dataset 18 days ago
published a
dataset 10 months ago
updated a
dataset 10 months ago
updated 7
datasets over 2 years ago
germank/hh-rlhf_with_features
Viewer • Updated • 19.1k • 16 • 1
germank/hh-rlhf_with_features_flan_t5_large
Viewer • Updated • 19.1k • 12
germank/hh-generated_flan_t5_large_with_features2_flan_t5_large
Viewer • Updated • 1.6k • 10
germank/hh-rlhf_with_features_flan_t5_large_lll_relabeled
Viewer • Updated • 9.57k • 10
germank/hh-rlhf_with_features_flan_t5_large_rx
Viewer • Updated • 19.1k • 13
germank/hh-rlhf_with_features_flan_t5_large-no_eos
Viewer • Updated • 19.1k • 11
germank/hh-generated_flan_t5_large_with_features2
Viewer • Updated • 1.6k • 10
updated a
dataset almost 3 years ago