bofenghuang
/

vigogne-falcon-7b-instruct

Text Generation

RefinedWebModel

text-generation-inference

Model card Files Files and versions Community

bofenghuang commited on Jul 5, 2023

Commit

5e1fdb1

•

1 Parent(s): d448eb1

Update readme

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -52,6 +52,8 @@ generated_outputs = model.generate(
         max_new_tokens=512,
     ),
     return_dict_in_generate=True,
 )
 generated_tokens = generated_outputs.sequences[0, input_length:]
 generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)

         max_new_tokens=512,
     ),
     return_dict_in_generate=True,
+    pad_token_id=tokenizer.eos_token_id,
+    eos_token_id=tokenizer.eos_token_id,
 )
 generated_tokens = generated_outputs.sequences[0, input_length:]
 generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)