You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
num_return_sequences should return multiple sequences.
But in real run, it only outputs one.
Reproduction
A test script:
import{pipeline}from"@huggingface/transformers";constgenerator=awaitpipeline("text-generation","onnx-community/Llama-3.2-1B-Instruct");consttext="Once upon a time, there was";constoutput=awaitgenerator(text,{temperature: 2,max_new_tokens: 10,repetition_penalty: 1.5,no_repeat_ngram_size: 2,num_beams: 2,num_return_sequences: 2,});console.log(output);
Output:
[
{
generated_text: 'Once upon a time, there was no such thing as social media. You were limited'
}
]
The text was updated successfully, but these errors were encountered:
System Info
Node.js / browser
Environment/Platform
Description
According to this doc:
num_return_sequences
should return multiple sequences.But in real run, it only outputs one.
Reproduction
A test script:
Output:
The text was updated successfully, but these errors were encountered: