unsloth

/

Meta-Llama-3.1-8B-Instruct

like 21

I used the code on hugging face, but I got error below:

ValueError Traceback (most recent call last)
----> 7 pipe = pipeline("text-generation", model="unsloth/Meta-Llama-3.1-8B-Instruct")

/usr/local/lib/python3.10/dist-packages/transformers/models/llama/configuration_llama.py in _rope_scaling_validation(self)
181 if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
--> 182 raise ValueError(
183 "rope_scaling must be a dictionary with two fields, type and factor, " f"got {self.rope_scaling}"
184 )

ValueError: rope_scaling must be a dictionary with two fields, type and factor, got {'factor': 8.0, 'high_freq_factor': 4.0, 'low_freq_factor': 1.0, 'original_max_position_embeddings': 8192, 'rope_type': 'llama3'}

The code I use is:
from transformers import pipeline
pipe = pipeline("text-generation", model="unsloth/Meta-Llama-3.1-8B-Instruct")

Please update your hugging face transfomers library! :)