Update README.md

README.md

@@ -1,3 +1,31 @@
 ---
 license: apache-2.0
+datasets:
+- BelleGroup/generated_train_0.5M_CN
+- JosephusCheung/GuanacoDataset
+language:
+- zh
+- en
 ---
+
+This is a Chinese instruction-tuning lora checkpoint based on llama-13B from [this repo's](https://github.com/Facico/Chinese-Vicuna) work
+
+You can use it like this: 
+
+
+```python
+  model = LlamaForCausalLM.from_pretrained(
+      "decapoda-research/llama-13b-hf",
+      load_in_8bit=LOAD_8BIT,
+      torch_dtype=torch.float16,
+      device_map="auto",
+  )
+  model = PeftModel.from_pretrained(
+      model,
+      "Chinese-Vicuna/Chinese-Vicuna-lora-13b-belle-and-guanaco",
+      torch_dtype=torch.float16,
+      device_map={'': 0}
+  )
+
+```
+