Modelpublic

nabin2004/AOS-qwen25-coder-7b-manim-gguf

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes20downloads

Model Card

AOS Qwen2.5-Coder-7B Manim SFT (GGUF)

Q4_K_M GGUF of the AOS Manim SFT merged model. Drop-in for Ollama and llama.cpp.

Model URL: https://huggingface.co/nabin2004/AOS-qwen25-coder-7b-manim-gguf

File	Description
`aos-qwen25-coder-7b-manim-Q4_K_M.gguf`	Quantized weights (~4–5 GB for 7B)
`Modelfile`	Ollama import template

Artifact	Repo
LoRA adapter	nabin2004/AOS-qwen25-coder-7b-manim-sft
Merged HF weights	nabin2004/AOS-qwen25-coder-7b-manim-merged

bash

ollama create aos-qwen25-coder-7b-manim -f Modelfile
ollama run aos-qwen25-coder-7b-manim

bash

./llama-cli -m aos-qwen25-coder-7b-manim-Q4_K_M.gguf -p "Animate a unit circle."