# Lightweight instruction fine-tuning

Phi-3.5-mini-instruct is a lightweight and advanced open-source model built on the dataset used by Phi-3, focusing on high-quality, inference-rich data. It supports a 128K token context length and has powerful multilingual and long-context processing capabilities.

SolaraV2 is an upgraded version of the original Solara model. It is a lightweight, instruction-fine-tuned language model developed by high school students, suitable for daily conversations and educational tasks.

This is a lightweight version of Llama-4-Scout-17B-16E-Instruct, providing users with a more streamlined usage option.

Doge 160M is a small language model based on dynamic masked attention mechanism, trained with supervised fine-tuning (SFT) and direct preference optimization (DPO).

This model was converted from microsoft/Phi-3-mini-4k-instruct to GGUF format using llama.cpp via ggml.ai's GGUF-my-repo space.

Phi-3 Mini is a lightweight, cutting-edge open-source model focused on high-quality, high-inference-density data, supporting a 4K context length.

Gemma is a lightweight open-source large language model developed by Google, offering a 2-billion-parameter version suitable for text generation tasks.