Text Generation
Transformers
Safetensors
English
Chinese
llama
conversational
text-generation-inference
Inference Endpoints
Siming Huang commited on
Commit
010ca0c
1 Parent(s): 09b16ec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -83,7 +83,7 @@ inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, ret
83
 
84
  outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)
85
 
86
- result = tokenizer.decode(outputs[0], skip_special_tokens=True)
87
  print(result)
88
  ```
89
 
 
83
 
84
  outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)
85
 
86
+ result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
87
  print(result)
88
  ```
89