Modelpublic

Fazmin/solus_v1_mistral-7b-instruct-v0.3-q4

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes16downloads

Model Card

Mistral 7B Instruct v0.3 — Solus v1

Mistral AI's 7B instruction-tuned model, version 0.3. Compared with earlier releases it carries an extended 32,768-token vocabulary and support for function calling.

Its reputation is for fluent, natural prose, which makes it a comfortable choice for drafting and rewriting. Apache 2.0 licensed, so there are no usage restrictions to pass along.

Specifications


Parameters	7B
Quantization	Q4KM
File size	4.07 GB
Minimum RAM	8.00 GB
Minimum VRAM	6.00 GB
Context length	32,768 tokens
SHA-256	`1270d22c0fbb3d092fb725d4d96c457b7b687a5f5a715abe1e818da303e562b6`

Single file: Mistral-7B-Instruct-v0.3-Q4_K_M.gguf

Quantization

Quantization performed at the Faculty of Engineering, McMaster University.

The GGUF conversion this build is derived from was produced by bartowski, and the weights here are a byte-for-byte copy of that file — the SHA-256 above matches the upstream artifact.

Provenance

—Original model: mistralai/Mistral-7B-Instruct-v0.3
—Upstream GGUF: bartowski/Mistral-7B-Instruct-v0.3-GGUF
—Mirrored for Solus, a desktop app for running language models entirely on your own machine.

Usage

bash

llama-cli -m Mistral-7B-Instruct-v0.3-Q4_K_M.gguf -cnv