QuantFactory/raspberry-3B-GGUF
This is quantized version of qnguyen3/raspberry-3B created using llama.cpp
Original Model Card
Prompt Format: ChatML
Trained Datasets:
- arcee-ai/EvolKit-20k
- LDJnr/Capybara
- and a private dataset
GGUFs: https://huggingface.co./mradermacher/raspberry-3B-GGUF
- Downloads last month
- 84
Model tree for QuantFactory/raspberry-3B-GGUF
Base model
Qwen/Qwen2.5-3B