rhaymison
/

Llama3-portuguese-luana-8b-instruct

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

rhaymison commited on Apr 26

Commit

98ca8e1

•

1 Parent(s): 05d0768

Update README.md

Files changed (1) hide show

README.md +0 -4

README.md CHANGED Viewed

@@ -197,9 +197,6 @@ You can use with Pipeline.
 ```python
 from transformers import pipeline
-stop_token = "<|eot_id|>"
-stop_token_id = tokenizer.encode(stop_token)[0]
 pipe = pipeline("text-generation",
                 model=model,
                 tokenizer=tokenizer,
@@ -210,7 +207,6 @@ pipe = pipeline("text-generation",
                 top_k=50,
                 top_p=0.95,
                 early_stopping=True,
-                eos_token_id=stop_token_id,
                 pad_token_id=tokenizer.eos_token_id,
                 )

 ```python
 from transformers import pipeline
 pipe = pipeline("text-generation",
                 model=model,
                 tokenizer=tokenizer,
                 top_k=50,
                 top_p=0.95,
                 early_stopping=True,
                 pad_token_id=tokenizer.eos_token_id,
                 )