README.md

metadata

library_name: transformers
tags:
  - gguf
  - quantized
  - llama.cpp
  - ollama
base_model: Qwen/Qwen2.5-Coder-3B-Instruct

Yalexis/qwen2.5-coder-3b-b2b-website-gguf

This is a Q4_K_M quantized GGUF version of Yalexis/qwen2.5-coder-3b-b2b-website.

Model Details

• Base Model: Qwen/Qwen2.5-Coder-3B-Instruct
• Fine-tuned Model: Yalexis/qwen2.5-coder-3b-b2b-website
• Quantization: Q4_K_M
• Format: GGUF
• File Size: 1.80 GB

Usage

Ollama

1. Create a Modelfile:

FROM ./qwen2.5-coder-3b-b2b-website-q4_k_m.gguf

2. Create the model:

ollama create qwen-b2b-website -f Modelfile

3. Run the model:

ollama run qwen-b2b-website

llama.cpp

./llama-cli -m qwen2.5-coder-3b-b2b-website-q4_k_m.gguf -p "Your prompt here"

LM Studio

Simply download this model in LM Studio and start chatting!

Model Information

This model was fine-tuned for B2B website generation with a 10k token context window.