Update README.md

README.md

@@ -1,5 +1,10 @@
 ---
 license: llama3.1
+language:
+- zh
+metrics:
+- bleu
+pipeline_tag: question-answering
 ---
  # 🚀 Introduction
 
@@ -7,6 +12,6 @@ This model is based on the [LLaMA3.1-8B-Chinese](https://huggingface.co/shenzhi-
 
 Data: We collected and cleaned high-quality medical knowledge data. With the help of commercial large models, we expanded the training set to about 8,000 high-quality instruction samples, covering key medical subfields such as treatment and pharmacology.
 
-Framework: DeepSpeed
+Framework: [DeepSpeed](https://github.com/deepspeedai/DeepSpeed)
 
-If you are interested in technologies such as DeepSpeed distributed training, LoRA fine-tuning, VLLM-based high-concurrency inference service deployment, or model quantization and compression, feel free to check out my [open-source project](https://github.com/RyanZxucheng/deepspeed-sft), provided for everyone to learn from.
+If you are interested in technologies such as DeepSpeed distributed training, LoRA fine-tuning, VLLM-based high-concurrency inference service deployment, or model quantization, feel free to check out my [open-source project](https://github.com/RyanZxucheng/deepspeed-sft), provided for everyone to learn from.