---
base_model: unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit
library_name: peft
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->
This is the model that is used to get the paper results for the MPCxR1 Qwen2.5 3B SFT GRPO model.
This model was evaluated on the 19.04.25. and trained on the 18.04.25 at 13:29:26.
The base model used for this training was "nibauman/race_llm_Qwen_3B_sft" [here](https://huggingface.co/nibauman/race_llm_Qwen_3B_sft)
This is the wandb training: https://wandb.ai/CoRL-heist-2025/mpc_grpo/runs/osa45as5?nw=nwusernibaumaneth