formalmathatepfl

university

https://www.epfl.ch/en/

AI & ML interests

None defined yet.

Recent Activity

Lemmy00 updated a dataset about 3 hours ago

formalmathatepfl/compiler_data

Lemmy00 updated a dataset about 3 hours ago

formalmathatepfl/rl_data

etiennebamas updated a dataset about 12 hours ago

formalmathatepfl/rl_data

View all activity

formalmathatepfl 's models 31

formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-ready

Text Generation • 308k • Updated 2 days ago • 480

formalmathatepfl/qwen3-sft-feedback-with-proof-repair-reasoning

Text Generation • 8B • Updated 3 days ago • 300

formalmathatepfl/qwen3-sft-feedback-with-proof-repair

Text Generation • 8B • Updated 4 days ago • 1.73k

formalmathatepfl/qwen3-cpt

Text Generation • 308k • Updated 17 days ago • 1.37k

formalmathatepfl/feedback-dropout-even

Text Generation • 308k • Updated Jun 25 • 5

formalmathatepfl/deepseek-prover-v2-feedback-grpo-2050

7B • Updated Jun 3 • 5

formalmathatepfl/qwen3-dropout-0.75

Text Generation • 308k • Updated Jun 3 • 7

formalmathatepfl/qwen3-dropout-0.5

308k • Updated Jun 3 • 3

formalmathatepfl/deepseek-prover-v2-feedback-grpo-800

7B • Updated May 25 • 5

formalmathatepfl/apertus-cpt-sft-classic

274k • Updated May 25 • 2

formalmathatepfl/apertus-cpt-sft-feedback

Text Generation • 274k • Updated May 25 • 5

formalmathatepfl/Apertus-8B-cpt

Text Generation • 274k • Updated May 23 • 7

formalmathatepfl/deepseek-prover-v2-grpo-800

Reinforcement Learning • 7B • Updated May 22 • 41

formalmathatepfl/qwen3-8b-sft-feedback-equal-compute

308k • Updated May 21 • 2 • 1

formalmathatepfl/qwen3-8b-sft-feedback

308k • Updated May 21 • 92

formalmathatepfl/deepseek-prover-v2-cpt-sft-feedback-1e

Text Generation • 7B • Updated May 19 • 20

formalmathatepfl/qwen3-8b-sft

Text Generation • 308k • Updated May 19 • 259

formalmathatepfl/deepseek-prover-v2-cpt-sft-1e

Text Generation • 7B • Updated May 17 • 19

formalmathatepfl/deepseek-prover-v2-cpt

Text Generation • 7B • Updated May 16 • 29

formalmathatepfl/Qwen30b-sft-feedback

211k • Updated May 14 • 1

formalmathatepfl/Qwen30b-sft-no-feedback

Text Generation • 211k • Updated May 14 • 7

formalmathatepfl/Qwen-30b-cpt

Text Generation • 211k • Updated May 12 • 5

formalmathatepfl/deepseek-math-7B-finetuned

Text Generation • 250k • Updated Apr 7 • 12

formalmathatepfl/Qwen3-8B-finetuned

Text Generation • 8B • Updated Mar 24 • 5

formalmathatepfl/llama-finetuned

Text Generation • 8B • Updated Mar 24 • 5

formalmathatepfl/OLMo-3-7B-finetuned

Text Generation • 528k • Updated Mar 24 • 7

formalmathatepfl/mistral-7B-v0.3-finetuned

Text Generation • 266k • Updated Mar 24 • 6

formalmathatepfl/deepseek-7B-finetuned

Text Generation • 250k • Updated Mar 24 • 10

formalmathatepfl/Apertus-8B-finetuned

Text Generation • 274k • Updated Mar 16 • 6

formalmathatepfl/DeepseekProverV2Finetuned01

Text Generation • 7B • Updated Feb 25 • 11