---
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
base_model:
- Qwen/Qwen3-8B
---

**[Click here to support our open-source dataset and model releases!](https://huggingface.co/spaces/sequelbox/SupportOpenSource)**

This is an **early alpha preview of the upcoming Esper 3 series for Qwen 3** - use at your own discretion! **[The full model is now available, click here!](https://huggingface.co/ValiantLabs/Qwen3-8B-Esper3)**

Esper 3 is a reasoning-chat finetune focused on coding, architecture, DevOps, and general reasoning chat. 

All training data generated synthetically by [Deepseek-R1 685b](https://huggingface.co/deepseek-ai/DeepSeek-R1) model. This sneak preview uses training data from our Titanium, Tachibana, and Raiden series of datasets. Final datasets used will be provided along the full release of Esper 3 - this preview release is only trained on a subselection of the data for early testing. Full model release coming soon!

See the **[Qwen 3 8b page](https://huggingface.co/Qwen/Qwen3-8B)** for sample prompting scripts or further information on the base model. **Esper 3 is a reasoning finetune: enable_thinking=True is recommended for all chats.**

Try the preview release out, see what you think, tell your friends :)

**[Please consider supporting our releases if you can. There's still time for a bottom-up AI revolution: the time to make a difference in how this turns out is now!](https://huggingface.co/spaces/sequelbox/SupportOpenSource)**

More Qwen 3 releases to come soon!

Do as you will.