lxcxjxhx/MSN_demo

---license: apache-2.0

Model Description

This model is a fine-tuning model based on Deepseek ai/Deepseek R1 and is currently in its early stages.
This model is committed to minimizing the model size as much as possible and providing models for a single professional field.

（This model is only used for learning purposes）

Model Details

DEMO 1:Attempt to reduce the size of the local model

DEMO 2:Reupload the usable quantized gguf model and attach a Llama.cpp compiled based on mysys2 for calling during model migration.

1.0：For the first fine-tuning and training, we attempted to use a smaller model and added a dataset from
huzaifa525 Medical_Sntelligence-Dataset_40k-Rows_of-Disease_info_Treatments_and_Sedical_QA based on the Lora training method