qwen3-0.6b-multicode-grpo-gguf

GGUF conversion of chaddy81/qwen3-0.6b-multicode-grpo.

Training Pipeline:

1. Base: Qwen/Qwen3-0.6B
2. SFT: chaddy81/qwen3-0.6b-multicode-sft
3. GRPO: chaddy81/qwen3-0.6b-multicode-grpo

Available Files

File	Quant	Size
qwen3-0.6b-multicode-grpo-q8_0.gguf	Q8_0	609.8 MB

Usage

With Ollama

huggingface-cli download chaddy81/qwen3-0.6b-multicode-grpo-gguf qwen3-0.6b-multicode-grpo-q8_0.gguf
echo "FROM ./qwen3-0.6b-multicode-grpo-q8_0.gguf" > Modelfile
ollama create qwen3-0.6b-multicode-grpo -f Modelfile
ollama run qwen3-0.6b-multicode-grpo

With llama.cpp

./llama-cli -m qwen3-0.6b-multicode-grpo-q8_0.gguf -p "Your prompt"