---
language:
- en
library_name: transformers
extra_gated_prompt: This model is exclusively available to Pro subscribers of [The
  Kaitchup](https://newsletter.kaitchup.com/). To gain access, subscribe to The Kaitchup Pro,
  [subscribe here](https://newsletter.kaitchup.com/subscribe). If you are already a Pro subscriber, you will find your access token on this [page](https://newsletter.kaitchup.com/p/introducing-minivoc-faster-and-memory-llms).
---

## Model Details

This is [nvidia/Mistral-NeMo-Minitron-8B-Base](https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Base) with a vocabulary reduced to 32k entries using the Minivoc (with average embeddings) approach. The model has been created, tested, and evaluated by The Kaitchup.


All the details about the Minivoc approach and evaluation in this article:
[Introducing Minivoc: Faster and Memory-Efficient LLMs Through Vocabulary Reduction](https://newsletter.kaitchup.com/p/introducing-minivoc-faster-and-memory-llms)


- **Developed by:** [The Kaitchup](https://newsletter.kaitchup.com/)
- **Language(s) (NLP):** English