appvoid/palmer-002-ultra

palmer

a better base model

palmer is a series of ~1b parameters language models fine-tuned to be used as base models instead of using custom prompts for tasks. This means that it can be further fine-tuned on more data with custom prompts as usual or be used for downstream tasks as any base model you can get. The model has the best of both worlds: some "bias" to act as an assistant, but also the abillity to predict the next-word from its internet knowledge base. It's a 1.1b llama 2 model so you can use it with your favorite tools/frameworks.

evaluation

Model	ARC_C	HellaSwag	PIQA	Winogrande
tinyllama-2t	0.2807	0.5463	0.7067	0.5683
palmer-001	0.2807	0.5524	0.7106	0.5896
tinyllama-2.5t	0.3191	0.5896	0.7307	0.5872
palmer-002	0.3242	0.5956	0.7345	0.5888
palmer-002-ultra	0.3319	0.5877	0.7252	0.6038

This is a continuation on palmer-x-002. As of now, this is the best overall model.

training

Training took ~7.5 P100 gpu hours. It was trained on 50,000 gpt-4 shuffled samples. palmer was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.

prompt

no prompt