Tholos-2B picks tools for AI assistants that run on your own computer. GGUF build and the training runs included.
AI & ML interests
Eschatia Labs is now on Hugging Face: https:// huggingface.co/eschatialabs We are an international open-source research lab. We publish small Al models that you can run and test on your own computer: • JevAlt decision models in English, Turkish and German. Karar-4B scores 96.8% on held-out Turkish decisions, against 87.1% for Kev-4B at the same size. • Tholos-2B picks tools for Al assistants on your own machine: 137 of 160 Tholos-Bench scenarios, against 112 for MiniCPM5-2B. • xdfdet detects deepfake videos and shows a heatmap of the face regions behind each decision (0.898 AUC on FaceForensics++). Every model has a GGUF build for Ilama.cpp and Ollama. More: https://eschatialabs.com
Recent Activity
View all activity
Organization Card
Eschatia Labs is an international open-source research lab. We publish small AI models, data and papers that people can run and test on their own computers. Our long-term goal is superintelligence.
| Work | What it does | Result |
|---|---|---|
| JevAlt decision models | Deem-4B, Karar-4B and Wähler-4B choose between options in English, Turkish and German and give a probability for each | Karar-4B, one of the best open Turkish decision models at 4B: 96.8% against Kev-4B's 87.1% on held-out Turkish decisions |
| Tholos-2B | A small model that picks tools for AI assistants on your own computer | 137 of 160 Tholos-Bench scenarios against MiniCPM5-2B's 112 |
| xdfdet | Eight deepfake video detectors with heatmaps that show which face regions drive each decision | 0.898 AUC on FaceForensics++ for the released detector |
| Eldalambë | One of the best research efforts on language preservation with small local models | Demo by invitation |
All open models and data: collection · GGUF builds for llama.cpp and Ollama: collection · eschatialabs.com · Mert Kaya · GitHub
models 0
None public yet
datasets 0
None public yet