SWE-RL Collection solving Github issues with Agentless scaffold and RL • 3 items • Updated about 1 hour ago
rasdani/deepseek_r1_llama_8b_swe_rl_8k_12_epochs_preds_100_v2 Viewer • Updated 26 days ago • 100 • 88
rasdani/deepseek_r1_llama_8b_swe_rl_8k_12_epochs_preds_100_v2 Viewer • Updated 26 days ago • 100 • 88