Large Language Model Fine-tuning & Inference

11 repos

Fine-tuned variants of Mistral-7B and other open-source language models optimized for instruction-following, text generation, and inference efficiency. These repositories focus on model adaptation techniques like DPO (Direct Preference Optimization), PPO (Proximal Policy Optimization), and pruning, paired with compatible inference infrastructure using tools like text-generation-inference and the transformers library. The cluster represents the practical ecosystem around deploying and customizing mid-size LLMs for production use cases.