Conversational AI & LLM Fine-tuning

13 repos

Fine-tuned language models and conversational AI systems built on foundation models like Mistral and other open-source LLMs. This cluster focuses on parameter-efficient adaptation techniques (PEFT/LoRA) to create specialized chat and text-generation models, enabling practical deployment of large language models with reduced computational overhead. Repositories here contain model checkpoints, training configurations, and implementations for building conversational assistants and chat applications.

Related clusters