Update README.md

README.md

@@ -136,7 +136,6 @@ pip install transformers
 
 ```python
 import sys
-from peft import PeftModel
 from transformers import LlamaForCausalLM, LlamaTokenizer
 
 
@@ -154,16 +153,13 @@ for s in sents:
     inputs = tokenizer(q, return_tensors="pt")
     inputs = inputs.to(device=device)
 
-    generate_ids = ref_model.generate(
+    generate_ids = model.generate(
         **inputs,
         max_new_tokens=120, 
         do_sample=True, 
         top_p=0.85, 
         temperature=1.0, 
-        repetition_penalty=1.0, 
-        eos_token_id=tokenizer.eos_token_id, 
-        bos_token_id=tokenizer.bos_token_id, 
-        pad_token_id=tokenizer.pad_token_id,
+        repetition_penalty=1.0
     )
 
     output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True)[0]