pankajmathur/RenCoder-Devstral-Small-2507

RenCoder-Devstral-Small-2507

This model is a SFT + RLVR (DPO+GRPO) version of mistralai/Devstral-Small-2507 on muliple agentic coding datasets (SWE-Bench, NVIDIA Terminal Corpus etc).

<img src="https://huggingface.co/pankajmathur/RenCoder-Ministral-8B-Instruct-2410/resolve/main/RenCoder.png" height="600" width="600" />

<strong> "Obsessed with building Open Source AGI, So am I ! Let's create together 🚀 <a href="https://www.linkedin.com/in/pankajam" target="_blank">https://www.linkedin.com/in/pankajam</a>" </strong>

Model Details

• —Base Model: mistralai/Devstral-Small-2507
• —Parameters: ~24B
• —Precision: bfloat16

Usage

License

This model inherits the Apache 2.0 license from the base Devstral-Small-2507 model.

Acknowledgements

• —Mistral AI for the Devstral-Small-2507 base model
• —Axolotl and NVIDIA-NeMo Gym for training infrastructure