Modelpublic

Fazmin/solus_v1_maincoder-1b-f16

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes25downloads

Model Card

Maincoder 1B — Solus v1

Maincode's 1B code-focused model, aimed at code generation and completion rather than open-ended conversation. Its size makes it viable on machines that cannot run a 7B coder at usable speed.

This build is F16 rather than a 4-bit quant, so it is full precision: larger on disk than a Q4 of the same model, but with no quantisation loss. Best suited to short scripts, snippets, and inline completions.

Specifications


Parameters	1B
Quantization	F16
File size	1.92 GB
Minimum RAM	4.00 GB
Minimum VRAM	not required
Context length	8,192 tokens
SHA-256	`4a3e551e0586cd4cd09bdd7ae5a37a9605461ec15ee9436a93a7852f27980b40`

Single file: Maincoder-1B-F16.gguf

Quantization

Quantization performed at the Faculty of Engineering, McMaster University.

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

Provenance

—Original model: Maincode/Maincoder-1B
—Upstream GGUF: Maincode/Maincoder-1B-GGUF
—Mirrored for Solus, a desktop app for running language models entirely on your own machine.

Usage

bash

llama-cli -m Maincoder-1B-F16.gguf -cnv