# instruction fine-tuning optimization

GGUF quantized version of Llama-3-8B-Instruct-64k, supporting multiple bit quantizations, suitable for text generation tasks.

An 8B parameter large language model developed based on winglian/Llama-3-8b-64k-PoSE, using PoSE technology to extend context length to 64k and optimized with DPO fine-tuning

Mistral-7B-Instruct-v0.2 is a large language model fine-tuned for instruction following based on Mistral-7B-v0.2, supporting a 32k context window with sliding window attention mechanism removed.