README / README.md
sd-inf's picture
Update README.md
b4485bf verified
---
title: README
emoji: 🦀
colorFrom: pink
colorTo: gray
sdk: static
pinned: false
---
![image](https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/kDrRRuP3q6cGvKzbZpb91.png)
We work on making small language models punch far above their weight while remaining lightweight and deployable on edge!
These are our models:
### Astral 1.5
> Astral is our open-data family, trained for STEM usage.
- Astral 1.5 4B ([link](https://huggingface.co/LucidityAI/Astral-1.5-4B-Preview))
### Astral
> Astral is our first open-data family, trained for STEM usage.
- Astral 14B ([link](https://huggingface.co/LucidityAI/Astral-14B))
- Astral 4B ([link](https://huggingface.co/LucidityAI/Astral-4B))
- Astral 0.6B Flash ([link](https://huggingface.co/LucidityAI/Astral-0.6B-Flash))
- Astral 4B Preview ([link](https://huggingface.co/LucidityAI/Astral-4B-Preview))
### Astral-Coder
> Astral models fine tuned for pure coding and agentic usage
- Astral 1B ([link](https://huggingface.co/LucidityAI/Astral-4B-Coder))
- Astral 0.6B Flash ([link](https://huggingface.co/LucidityAI/Astral-0.6B-Flash-Coder))
### Synth
- Synth 2 ([link](https://huggingface.co/LucidityAI/Synth-2))
- Synth 1.5 ([link](https://huggingface.co/LucidityAI/Synth-1.5))
- Synth 1 ([link](https://huggingface.co/LucidityAI/Synth-1))
### RedTeamer
> RedTeamer is a model that generates jailbreaks that can be used for testing against LLMs.
- RedTeamer 1 ([link](https://huggingface.co/LucidityAI/RedTeamer-v1))
### Koishi
> Koishi is a data synthesis LLM that generates CoT traces for non-CoT examples.
- Koishi 1 ([link](https://huggingface.co/LucidityAI/Koishi-1))
### Kiwi (Depreciated)
> Kiwi is a family of models trained for general STEM tasks.
- Kiwi 1.7B Nano ([link](https://huggingface.co/LucidityAI/kiwi-1.7b-nano))
- Kiwi 4B Mini ([link](https://huggingface.co/LucidityAI/kiwi-4b))
- Kiwi 8B ([link](https://huggingface.co/LucidityAI/Kiwi-8b))
### Lumi (Depreciated)
> Depreciated STEM tuned models based on Qwen2.5 3B
- Lumi 1.5 (3B) ([link](https://huggingface.co/LucidityAI/Lumi-1.5))
- Lumi 1 (3B) ([link](https://huggingface.co/LucidityAI/Lumi-1))