Article
1
Pierre Erbacher
erbacher
AI & ML interests
None yet
Recent Activity
published an article 1 day ago
Distribution Matching Prevents Mode Collapse in Training Reasoning Models updated a model 4 months ago
erbacher/Qwen2.5-Kimina-1.7B-SFT updated a dataset 4 months ago
erbacher/trl-NuminaMath-LEANOrganizations
models 48
erbacher/Qwen2.5-Kimina-1.7B-SFT
Text Generation • 2B • Updated • 4
erbacher/wiki_categories
Updated
erbacher/Llama-3.2-Tulu-3-1B-SFT
1B • Updated • 1
erbacher/llama3.2-1B-MATH
Text Generation • 1B • Updated • 3
erbacher/llama-1B-online-dpo
Updated
erbacher/zephyr-rag-agent-webgpt
Text Generation • 3B • Updated • 2 • 1
erbacher/zephyr-3b-rag-agent-webgpt
Updated
erbacher/gptneo-125M-acco-32a
Text Generation • 0.1B • Updated
erbacher/gptneo-125M-ddp-32a
Text Generation • 0.1B • Updated
erbacher/gpt-neo-125M-ddp
Text Generation • 0.1B • Updated
datasets 20
erbacher/trl-NuminaMath-LEAN
Viewer • Updated • 9.48k • 7
erbacher/LeanRank-corpus
Viewer • Updated • 249k • 9
erbacher/LeanRank-test
Viewer • Updated • 6.57k • 10
erbacher/LeanRank-data
Viewer • Updated • 2.09M • 36
erbacher/MATH_TTT
Viewer • Updated • 12k • 9
erbacher/open-math-instruct-steps
Updated • 9
erbacher/rag-n-roll-webgpt-deduplicated
Viewer • Updated • 50.8k • 10
erbacher/rag-and-roll-hagrid-deduplicated
Viewer • Updated • 3.71k • 19
erbacher/ragnroll-webgpt
Viewer • Updated • 13.8k • 10
erbacher/rag-and-roll-hagrid
Viewer • Updated • 2.64k • 11 • 1