Modelpublic

Fazmin/solus_v1_qwen2.5-coder-7b-instruct-q4

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes40downloads

Model Card

Qwen2.5 Coder 7B Instruct — Solus v1

The code specialist of the Qwen2.5 family, continued-pretrained on a large code-heavy corpus on top of the general Qwen2.5 base. It writes, explains, reviews, and repairs code across a wide range of languages, and it is competitive with much larger general models on coding tasks.

Apache 2.0 licensed. This is the model to pick in Solus when the work is mostly programming.

Specifications


Parameters	7B
Quantization	Q4KM
File size	4.36 GB
Minimum RAM	8.00 GB
Minimum VRAM	6.00 GB
Context length	32,768 tokens
SHA-256	`1664fccab734674a50763490a8c6931b70e3f2f8ec10031b54806d30e5f956b6`

Single file: Qwen2.5-Coder-7B-Instruct-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: Qwen/Qwen2.5-Coder-7B-Instruct
—Upstream GGUF: bartowski/Qwen2.5-Coder-7B-Instruct-GGUF
—Mirrored for Solus, a desktop app for running language models entirely on your own machine.

Usage

bash

llama-cli -m Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf -cnv