This model is a fine-tuned version of TinyLlama on WizardVicuna Dataset. It should be fully compatible with Vicuna-v1.5 series thanks to https://huggingface.co./Jiayi-Pan/Tiny-Vicuna-1B. I just made it llamafile version. Here is how the model was running in case if you are interested
https://github.com/Mozilla-Ocho/llamafile/issues/242#issuecomment-1930700064
To run in windows just run this attach exe as it is. For linux systems just rename the file removing the .exe and run the llamafile as you run any binary after chmod. That's it.