moheith/Yulya-Llama-3.1-8B
Text Generation • 8B • Updated • 44
Yulya
💙 A family of fine-tuned conversational AI models across multiple architectures and sizes — built to bring Yulya's expressive, playful and chaotic.
Note 👑Yulya Llama 3.1 8B: The flagship Yulya model — choose it for the strongest conversational capabilities, richer responses, and the full Yulya experience.
moheith/Yulya-Qwen2.5-7B
Text Generation • 8B • Updated • 66Note 💜 Yulya Qwen2.5 7B: Choose it for powerful conversations and strong capabilities with Qwen2.5, while keeping Yulya’s chaotic and expressive personality.
moheith/Yulya-Qwen2.5-1.5B
Text Generation • 2B • Updated • 52Note 💙 Yulya Qwen2.5 1.5B: The balanced sweet spot — choose it for a great mix of conversational capability, speed, and lower hardware requirements.
moheith/Yulya-Llama-3.2-1B
Text Generation • 1B • Updated • 13Note 💛 Yulya Llama 3.2 1B: Choose it for a lightweight and fast Llama-based Yulya experience, ideal for local apps and interactive AI projects.
moheith/Yulya-Qwen2.5-0.5B
Text Generation • 0.5B • Updated • 44Note 💚 Yulya Qwen2.5 0.5B: Choose it for fast inference and low hardware requirements while still getting Yulya’s playful and chaotic personality.
moheith/Yulya-SmolLM2-135M
Text Generation • 0.1B • Updated • 93Note 🧡 Yulya SmolLM2 135M: The smallest experimental Yulya model — choose it for extremely lightweight inference, low-end hardware, and fast experimentation.