Researching and developing specialized Large Language Models for software security and automated vulnerability repair. Primary interests include fine-tuning domain-specific Code-LLMs (FineSec-AI), synthetic dataset curation, zero false-positive benchmark evaluation, and quantized edge deployment for local AppSec tooling.
Trained another version of llama3-8b-instruct which beats the base model. This time without losing too many points on gsm8k benchmark. Again, using AutoTrain π₯ pip install autotrain-advanced Trained model: https://huggingface.co/abhishek/autotrain-llama3-orpo-v2
Here it is, an Adaptive AI Assistant (AAA) only made possible through open-source, incredibly inspiring, well done to the Open Interpreter teamππΌππΌ