Update README.md

README.md

@@ -29,19 +29,16 @@ from peft import PeftModel
 from transformers import GenerationConfig, LlamaForCausalLM, LlamaTokenizer
 
 
-max_memory = {i: "15GIB" for i in range(torch.cuda.device_count())}
-tokenizer = LlamaTokenizer.from_pretrained(base_model)
+tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/llama-7b-hf")
 model = LlamaForCausalLM.from_pretrained(
-    base_model,
+    "decapoda-research/llama-7b-hf",
     load_in_8bit=True,
     torch_dtype=torch.float16,
     device_map="auto"
-    max_memory=max_memory
 )
 model = PeftModel.from_pretrained(
     model,
-    lora_weights,
-    torch_dtype=torch.float16,
-    max_memory=max_memory
+    "DataAgent/llama-7b-alpaca-zh-20k",
+    torch_dtype=torch.float16
 )
 ```