Edit model card

A model trained on a dataset of 1.35 million rows of Yahoo Answers Q and A. ( https://huggingface.co/datasets/community-datasets/yahoo_answers_topics ) It does not chat well and will fall apart at longer contexts, but it does give unique responses. It also believes the year is 2006... so yea, have fun!

Model uses ChatML formatting and works "best" with single round QA. System prompt is "You are a helpful assistant."

image/png

Downloads last month
11
Safetensors
Model size
12.2B params
Tensor type
BF16
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for cgato/Nemo-12b-TheAnswer-v0.1-E2

Quantizations
1 model