RichardErkhov/double7_-_vicuna-68m-4bits

Quantization made by Richard Erkhov.

vicuna-68m - bnb 4bits

Model creator: https://huggingface.co/double7/
Original model: https://huggingface.co/double7/vicuna-68m/

Original model description:

license: apache-2.0 datasets: - anon8231489123/ShareGPT_Vicuna_unfiltered language: - en pipeline_tag: text-generation

Model description

This is a Vicuna-like model with only 68M parameters, which is fine-tuned from LLaMA-68m on ShareGPT data.

The training setup follows the Vicuna suite.

The model is mainly developed as a base Small Speculative Model in the MCSD paper. As a comparison, it can be better aligned to the Vicuna models than LLaMA-68m with little loss of alignment to the LLaMA models.

Draft Model	Target Model	Alignment
LLaMA-68/160M	LLaMA-13/33B	😃
LLaMA-68/160M	Vicuna-13/33B	😟
Vicuna-68/160M	LLaMA-13/33B	😃
Vicuna-68/160M	Vicuna-13/33B	😃