README.md

Quantization made by Richard Erkhov.

Github

Discord

Request more models

HelpingAI-Lite-2x1B - AWQ

• Model creator: https://huggingface.co/OEvortex/
• Original model: https://huggingface.co/OEvortex/HelpingAI-Lite-2x1B/

Original model description:

language:

• en metrics:
• accuracy library_name: transformers base_model: OEvortex/HelpingAI-Lite tags:
• HelpingAI
• coder
• lite
• Fine-tuned
• moe
• nlp license: other license_name: hsul license_link: https://huggingface.co/OEvortex/vortex-3b/raw/main/LICENSE.md

---

HelpingAI-Lite

Subscribe to my YouTube channel

Subscribe

The HelpingAI-Lite-2x1B is a MOE (Mixture of Experts) model, surpassing HelpingAI-Lite in accuracy. However, it operates at a marginally reduced speed compared to the efficiency of HelpingAI-Lite. This nuanced trade-off positions the HelpingAI-Lite-2x1B as an exemplary choice for those who prioritize heightened accuracy within a context that allows for a slightly extended processing time.

Language

The model supports English language.