formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-200-unmasked download history
formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-200-unmasked is an 8.2B-parameter model model by formalmathatepfl. In the last 30 days it was downloaded 76 times (4 in the last 7 days), and 76 times in total.
It ranks #212,776 on the Hub by monthly downloads.
It has 0 likes.
1 models build on qwen3-sft-feedback-with-proof-repair-rl-200-unmasked: 0 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 380 times in the last 30 days. See the qwen3-sft-feedback-with-proof-repair-rl-200-unmasked galaxy.
Most downloaded derivatives
- etiennebamas/feedback-grpo-step-200-reasoning-sft (finetune), 304 downloads in 30 days
Open formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-200-unmasked on Hugging Face