costinstroie/qwen2.5-1.5b-medical-sft-GGUF

qwen2.5-1.5b-medical-sft-GGUF

GGUF conversion of PrasannaPaithankar/qwen2.5-1.5b-medical-sft-lora, a Qwen2.5-1.5B model fine-tuned on medical data (full merged fp16 weights despite the "lora" in the name). Converted with llama.cpp (b8733); all credit for the fine-tune goes to the original author.

The embedded chat template is the standard Qwen ChatML template shipped with the source repo.

llama-cli -m qwen2.5-1.5b-medical-sft-Q8_0.gguf

Notes

• —The source repository has no model card, so its training data, base checkpoint and license are not documented. Apache-2.0 is assumed from the Qwen2.5-1.5B base; verify with the original author before relying on it.
• —Not for clinical use — outputs may be wrong and must be reviewed by a qualified professional.