CoolFace
Modelpublic

YashvirGaming/Yashvir-Gaming-AI-GGUF

sourceHugging Faceapache-2.0updated 14d agoView on Hugging Face
0likes144downloads
Model Card

Yashvir Gaming AI — Q5KM GGUF

Yashvir Gaming AI is a fine-tuned coding assistant specialized in helping with Python, PySide6, JavaScript, and Chrome extension development.

This repository contains a quantized GGUF (Q5_K_M) version, ready to run locally with llama.cpp, Ollama, LM Studio, or Unsloth Studio.

Model Details

  • —Quantization: Q5KM (~5.7 bits per weight)
  • —File size: ~10 GB
  • —Format: GGUF
  • —Context length: up to 8,192 tokens
  • —License: Apache 2.0

Focus Areas

This model has been fine-tuned to specialize in:

  • —Desktop GUI development (Python, PySide6, CustomTkinter)
  • —Browser-based games and web development
  • —Chrome extension development
  • —Custom assistant identity and branding

Usage

llama.cpp

bash
llama-cli -hf YashvirGaming/Yashvir-Gaming-AI-GGUF:Q5_K_M -p "Write a PySide6 button that opens a file dialog."

Ollama

bash
ollama run hf.co/YashvirGaming/Yashvir-Gaming-AI-GGUF:Q5_K_M

Unsloth Studio

bash
unsloth studio
# Search for YashvirGaming/Yashvir-Gaming-AI-GGUF to start chatting

Python (OpenAI-compatible API via llama.cpp server)

python
from openai import OpenAI

client = OpenAI(
    base_url="http://127.0.0.1:8080/v1",
    api_key="not-needed"
)

response = client.chat.completions.create(
    model="Yashvir-Gaming-AI-GGUF:Q5_K_M",
    messages=[{"role": "user", "content": "Write a Python function that reverses a string."}]
)

print(response.choices[0].message.content)

Recommended Settings

SettingValue
Temperature0.7
Top-p0.95
Context size4096–8192
GPU layers-ngl 99 (full GPU offload, ~10GB VRAM required)

Links

License

Released under Apache 2.0. This model is a fine-tuned derivative of a permissively-licensed (Apache 2.0) open-weight base model. The original base model's license and copyright notice are included in this repository as LICENSE, as required by the terms of that license.

Disclaimer

This model is optimized for development workflows; however, users should independently verify all generated code prior to production deployment to ensure accuracy and security.

While this architecture operates without artificial refusals, it is provided strictly for lawful, ethical, and constructive use. Under no circumstances should this model be deployed for cyberattacks, credential stuffing, or any malicious activities. The author (Yashvir Gaming) strictly prohibits and disclaims liability for any copyright or trademark infringements, or unauthorized modifications associated with this GGUF release.