Why didn't my output show up |startthought|? Such tokens
Why didn't my output show up |startthought|? Such tokens
here is my code：
from transformers import pipeline
local_model_path = "/localpath/Mistral-quiet-star-demo"
pipe = pipeline("text-generation", model=local_model_path, tokenizer=local_model_path)
text = '''user: "hi there. id like to build a time machine. how might i go about achieving this?"'''
output = pipe(text, max_length=50)
print(output)
Loading checkpoint shards: 100%
3/3 [00:06<00:00, 2.15s/it]
Truncation was not explicitly activated but max_length is provided a specific value, please use truncation=True to explicitly truncate examples to max length. Defaulting to 'longest_first' truncation strategy. If you encode pairs of sequences (GLUE-style) with the tokenizer you can select this strategy more precisely by providing a specific strategy to truncation.
Setting pad_token_id to eos_token_id:2 for open-end generation.
[{'generated_text': 'user: "hi there. id like to build a time machine. how might i go about achieving this?"\n response: "you could start by reading up on the principles of relativity and quantum mechanics, then look into current research on time'}]