formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-200-unmasked
8B • Updated • 61
formalmathatepfl
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 22
formalmathatepfl/classic-reasoning-grpo-step-175
8B • Updated • 18
formalmathatepfl/qwen3-8b-classic-low-timeouts-grpo
8B • Updated • 22
formalmathatepfl/qwen3-8b-classic-hybrid-grpo
8B • Updated • 19
formalmathatepfl/feedback-grpo-reasoning-sft
Text Generation • 8B • Updated • 483
formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-125-unmasked
8B • Updated • 31
formalmathatepfl/classic-grpo-reasoning-sft
Text Generation • 8B • Updated • 579
formalmathatepfl/qwen3-8b-feedback-non-base-with-repair
Text Generation • 8B • Updated • 414
formalmathatepfl/qwen3-8b-feedback-with-repair
Text Generation • 8B • Updated • 234
formalmathatepfl/qwen3-8b-feedback-no-repair
Text Generation • 8B • Updated • 274
datasets 12
formalmathatepfl/reasoning_data
Viewer • Updated • 178k • 330
formalmathatepfl/rl_data
Viewer • Updated • 213k • 419
formalmathatepfl/feedback_data_training_chat_template
Viewer • Updated • 2.76M • 92
formalmathatepfl/feedback_data_training
Viewer • Updated • 3.55M • 857 • 1
formalmathatepfl/lean-eval-benchmark
Viewer • Updated • 68.9k • 58
formalmathatepfl/qwen3-classic-rl-distl
Viewer • Updated • 87.3k • 48
formalmathatepfl/qwen3-feedback-rl-distl
Viewer • Updated • 87.3k • 70
formalmathatepfl/compiler_data
Viewer • Updated • 4.84M • 126
formalmathatepfl/sft-one_shot-cleaned
Viewer • Updated • 1.82M • 279
formalmathatepfl/sft_classic_numina
Viewer • Updated • 99.8k • 42