metadata

license: llama2
datasets:
  - anon8231489123/ShareGPT_Vicuna_unfiltered
language:
  - en
pipeline_tag: text-generation
tags:
  - eagle

EAGLE heads weights for WizardLM

This model is trained using the repository https://github.com/SafeAILab/EAGLE (commit: cab744bdab6f6083fa04f19879475e5acbd1706e).

It shows approximately 2x speed up for WizardLM model evaluate on ShareGPT dataset.

To run the code please follow the instruction in https://github.com/SafeAILab/EAGLE . You will also need to download the base model weights from WizardLM-7b-V1.0