Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Model card v5: add agent scenario examples (error diagnosis, N+1 detection, code modification)

Model card v4: fix production-ready claim, add metric circularity note, strengthen licensing language

Model card v3: added benchmark limitations, ethical considerations, reproducibility, contact

Update model card v2: featured DPO story, example output, honest review fixes

Add GGUF Q2_K quantization

Add GGUF Q3_K_M quantization

Add GGUF Q4_K_S quantization

Add GGUF Q4_K_M quantization

Add GGUF Q6_K quantization

Add GGUF Q8_0 quantization

Initial release: merged fp16 model + model card

initial commit