|  | |
| # Try to get it to answer your questions, if you even can... | |
| A frankenMoE of [TinyLlama-1.1B-1T-OpenOrca](https://huggingface.co/jeff31415/TinyLlama-1.1B-1T-OpenOrca) | |
| [TinyLlama-1.1B-intermediate-step-1195k-token-2.5T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T) | |
| and [tiny-llama-1.1b-chat-medical](https://huggingface.co/SumayyaAli/tiny-llama-1.1b-chat-medical) | |
| # Most 1.1B models are decoherent and can't even answer simple questions. I found the models that don't fail in this regard, then mashed 32 copies of those 3 models together into a 32x MoE |