Update README.md

README.md

@@ -21,3 +21,39 @@ The following `bitsandbytes` quantization config was used during training:
 
 ### 额外说明
 这是基于LLaMA使用QLoRA技术微调的一个适配器模型
+
+```
+# imports
+from peft import PeftModel
+from transformers import GenerationConfig, LlamaForCausalLM, LlamaTokenizer
+import torch
+
+# create tokenizer
+base_model = "huggyllama/llama-7b"
+tokenizer = LlamaTokenizer.from_pretrained(base_model)
+
+# base model
+model = LlamaForCausalLM.from_pretrained(
+        base_model,
+        torch_dtype=torch.float16,
+        device_map="auto",
+    )
+
+# LORA PEFT adapters
+adapter_model = "AtomGradient/adjust_llama-7b"
+
+model = PeftModel.from_pretrained(
+        model,
+        adapter_model,
+        #torch_dtype=torch.float16,
+    )
+model.eval()
+
+# prompt
+prompt = "美国的总统是谁"
+inputs = tokenizer(prompt, return_tensors="pt")
+
+# Generate
+generate_ids = model.generate(**inputs, max_new_tokens=30)
+print(tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0])
+```