universitytehran
/

PersianMind-v1.0

Text Generation

text-generation-inference

Model card Files Files and versions Community

Pedram Rostami commited on Jan 22

Commit

49513bb

•

1 Parent(s): 9aad44b

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -73,7 +73,7 @@ input_tokens = input_tokens.to(device)
 generate_ids = model.generate(**input_tokens, max_new_tokens=512, do_sample=False, repetition_penalty=1.1)
 model_output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
-print(model_output[len(model_input) + 1: ])
 ```
 ### How to Quantize the Model

 generate_ids = model.generate(**input_tokens, max_new_tokens=512, do_sample=False, repetition_penalty=1.1)
 model_output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+print(model_output[len(model_input):])
 ```
 ### How to Quantize the Model