TheBloke/Thespis-Mistral-7B-v0.5-AWQ

Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported by a grant from andreessen horowitz (a16z) — Model creator: c.gato — Original model: Thespis Mistral 7B v0.5 This repo contains AWQ model files for c.gato’s Thespis Mistral 7B v0.5. These files were quantised using hardware kindly provided by Massed Compute. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. — Text Generation Webui — using Loader: AutoAWQ — vLLM — Llama and Mistral models only — Hugging Face Text Generation Inference (TGI) — AutoAWQ — for use from Python code AWQ model(s) for GPU inference. GPTQ models for GPU inference, with multiple quantisation parameter options. 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference c.gato’s original unquantised fp16 model in pytorch format, for GPU inference and for further conversions For my first release of AWQ models, I am releasing 128g models only. I will consider…

Модальности:
Генерация текста

Задача: Генерация текста
Автор: TheBloke
Теги: mistral, not-for-all-audiences, text-generation-inference, 4-bit, awq
Лайков: 3  |  Загрузок: 13

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.