# Lightweight quantization

SmolVLM2-2.2B-Instruct is a vision-language model with a parameter scale of 2.2B, focusing on video text-to-text tasks and supporting English.

This is a weighted/matrix quantized version of Casual-Autopsy/Llama-3-VNTL-Yollisa-8B, suitable for English and Japanese processing, specifically targeting Japanese media, otaku media, and visual novels (VNs).

A quantized version based on Alibaba NLP/gte-Qwen2-1.5B-instruct, primarily used for sentence similarity computation and text embedding tasks.

This is the GGUF format conversion version of the gemma-2-baku-2b-it model from the rinna company, applying K quantization and iMatrix technology

1.3B parameter GPT-NeoX model pretrained on 31.3GB Vietnamese data