LLM Fine-tuning & Text Generation

10 repos

This cluster focuses on fine-tuning and inference for large language models, with emphasis on conversational and text generation capabilities. The repositories center on adapting pre-trained models like Qwen2, Gemma, and Llama3 for specific tasks, using frameworks like transformers and safetensors for efficient model handling. Developers exploring this cluster will find practical implementations of full fine-tuning pipelines, model optimization techniques, and deployment patterns for production language model applications.