CoolFace
Modelpublic

sthaps/openthaigpt-thaillm-8b-instruct-v0.7.2-research-preview-gguf

sourceHugging Faceapache-2.0updated 9mo agoView on Hugging Face
0likes635downloads
Model Card

openthaigpt-thaillm-8b-instruct-v0.7.2-research-preview - GGUF

About

This repository contains GGUF weights for openthaigpt/openthaigpt-thaillm-8b-instruct-v0.7.2-research-preview.

For a convenient overview and download list, visit our model page.

Usage

If you are unsure how to use GGUF files, refer to the llama.cpp documentation for more details.

Llama.cpp CLI

bash
./llama-cli -m openthaigpt-thaillm-8b-instruct-v0.7.2-research-preview-q4_k_m.gguf -p "Hello!"

Provided Quants

(sorted by size, not necessarily quality)

LinkTypeSize/GBNotes
GGUFq2_k3.06very low quality, for testing
GGUFq3km3.84
GGUFq4_04.45
GGUFq4km4.68recommended, good balance

Thanks

Special thanks to the llama.cpp team for their amazing work.