Issues with LLAMA 3-8B-Instruct model

[madhusrivatsav]

Hi

I get this error while using SliceGPT for the LLama Instruct models:
ValueError: rope_scaling must be a dictionary with two fields, type and factor, got {'factor': 8.0, 'low_freq_factor': 1.0, 'high_freq_factor': 4.0, 'original_max_position_embeddings': 8192, 'rope_type': 'llama3'}

To overcome this, I updated the Transformers package version to 4.44.2. However, slice GPT is not compatible with this transformer version. Can anyone please help in solving this issue?