# instruction fine-tuning

Aya-23 is an open-weight research version of an instruction fine-tuned model with highly advanced multilingual capabilities, supporting 23 languages.

This model is an INT4 quantized version of Mistral-Small-3.1-24B-Instruct-2503, using the GPTQ algorithm to reduce weights from 16-bit to 4-bit, significantly decreasing disk size and GPU memory requirements.

Gemma 3 is an instruction-tuned large language model developed by Google. This repository provides its 27B parameter W4A16 quantized version, significantly reducing hardware requirements

This is a 4-bit quantized version converted from the allenai/OLMo-2-0325-32B-Instruct model, optimized for the MLX framework and suitable for text generation tasks.

GGUF quantized version of Llama-3-8B-Instruct-32k-v0.1, supporting multi-bit quantization, suitable for text generation tasks.

Norocetacean 20B 10K is a large language model based on the Llama 2 architecture, fine-tuned to support Chinese tasks.