update usage

README.md

@@ -65,29 +65,29 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 tokenizer = AutoTokenizer.from_pretrained("DAMO-NLP-MT/polylm-13b", use_fast=False)
 
-model = AutoModelForCausalLM.from_pretrained(str(ckpt_path), device_map="auto")
+model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-MT/polylm-13b", device_map="auto")
 model.eval()
 
-input_doc = "Beijing is the capital of China. Translate this sentence from English to Chinese."
+input_doc = f"Beijing is the capital of China.\nTranslate this sentence from English to Chinese."
 
 inputs = tokenizer(input_doc, return_tensors="pt")
 
 generate_ids = model.generate(
-	inputs.input_ids, 
-	attention_mask=inputs.attention_mask, 
-	do_sample=True, 
-	max_new_tokens=128,
-	top_k=10, 
-	top_p=0.9, 
-	temperature=0.7, 
-	repetition_penalty=1.0, 
-	num_return_sequences=5
+	inputs.input_ids,
+  attention_mask=inputs.attention_mask,
+  do_sample=False,
+  num_beams=4,
+  max_length=128,
+  early_stopping=True
 )
 
 decoded = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
 
 print(f">>> {decoded}")
 
+### results
+### Beijing is the capital of China.\nTranslate this sentence from English to Chinese.\\n北京是中华人民共和国的首都。\n ...
+
 ```
 
 </details>