infrastructure-assistant-7b-gguf

This is a GGUF conversion of lokegud/infrastructure-assistant-7b, which is a LoRA fine-tuned version of Qwen/Qwen2.5-7B-Instruct.

Model Details

• Base Model: Qwen/Qwen2.5-7B-Instruct
• Fine-tuned Model: lokegud/infrastructure-assistant-7b
• Training: Supervised Fine-Tuning (SFT) with TRL
• Format: GGUF (for llama.cpp, Ollama, LM Studio, etc.)

Available Quantizations

File	Quant	Size	Description	Use Case
infrastructure-assistant-7b-f16.gguf	F16	~1GB	Full precision	Best quality, slower
infrastructure-assistant-7b-q8_0.gguf	Q8_0	~500MB	8-bit	High quality
infrastructure-assistant-7b-q5_k_m.gguf	Q5_K_M	~350MB	5-bit medium	Good quality, smaller
infrastructure-assistant-7b-q4_k_m.gguf	Q4_K_M	~300MB	4-bit medium	Recommended - good balance

Usage

With llama.cpp

# Download model
huggingface-cli download lokegud/infrastructure-assistant-7b-gguf infrastructure-assistant-7b-q4_k_m.gguf

# Run with llama.cpp
./llama-cli -m infrastructure-assistant-7b-q4_k_m.gguf -p "Your prompt here"

With Ollama

1. Create a Modelfile:

FROM ./infrastructure-assistant-7b-q4_k_m.gguf

2. Create the model:

ollama create my-model -f Modelfile
ollama run my-model

With LM Studio

1. Download the .gguf file
2. Import into LM Studio
3. Start chatting!

License

Inherits the license from the base model: Qwen/Qwen2.5-7B-Instruct

Citation

@misc{infrastructure_assistant_7b_gguf,
  author = {lokegud},
  title = {infrastructure-assistant-7b-gguf},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/lokegud/infrastructure-assistant-7b-gguf}
}

---

Converted to GGUF format using llama.cpp