arXiv-WVY-43M
arXiv-WVY-43M is a 43.5M parameter tiny language model developed by Starpower Technology intended for autonomous research. This is...
arXiv-WVY-43M is a 43.5M parameter tiny language model developed by Starpower Technology intended for autonomous research. This is...
Kimi K2 Thinking — это новейшая, наиболее способная версия модели мышления с открытым исходным кодом. Начиная с Kimi...
This model is a mixed int4 model with groupsize 128 and symmetric quantization of deepseek-ai/DeepSeek-V3.1-Terminus generated by intel/auto-round...
This update maintains the model’s original capabilities while addressing issues reported by users, including: — Language consistency: Reducing...
📰 Tech Blog | 📄 Paper Kimi K2-Instruct-0905 is the latest, most capable version of Kimi K2. It...
DeepSeek-V3.1 — это гибридная модель, поддерживающая как режим мышления, так и режим без мышления. По сравнению с предыдущей...
This tiny model is for debugging. It is randomly initialized with the config adapted from moonshotai/Kimi-K2-Instruct. Модальности:Генерация текста...
> [!NOTE] > Включает исправления шаблонов чата! Для llama.cpp используйте —jinja > Unsloth Dynamic 2.0 обеспечивает превосходную точность...
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. Assembly of Experts Chimera model constructed with...
It’s a 4-bit AWQ quantization of DeepSeek-R1-0528 671B model, it’s suitable for use with GPU nodes like 8xA100/8xH20/8xH100...