ai-jacob-watkins/qwen3-4b-medical-mcqa-4bit
038
V3 LoRA fused: bake LoRA weights into base model, re-quantize 4-bit. No separate adapter needed.
Upload Qwen3-4B Medical MCQA 4-bit (quantised by CMPO)
initial commit
V3 LoRA fused: bake LoRA weights into base model, re-quantize 4-bit. No separate adapter needed.
Upload Qwen3-4B Medical MCQA 4-bit (quantised by CMPO)
initial commit