PEFT
Safetensors
llama-factory
lora
Generated from Trainer
DeepSWE-Verifier / training_loss.png
michaelzhiluo's picture
Copy model from r2e-edits/deepswe-swebv-eval-n16-verifier-qwen3-lora64-agent-priority-v1
ffdc142 verified
download
history contribute delete
27.9 kB
training_loss.png