turboderp's picture
Update README.md
b15b7ad verified
EXL2 quants of [Phi-3 mini 128k instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)
[~~2.50 bits per weight~~](https://huggingface.co/turboderp/Phi-3-mini-128k-instruct-exl2/tree/2.5bpw) (broken)
[3.00 bits per weight](https://huggingface.co/turboderp/Phi-3-mini-128k-instruct-exl2/tree/3.0bpw)
[4.00 bits per weight](https://huggingface.co/turboderp/Phi-3-mini-128k-instruct-exl2/tree/4.0bpw)
[5.00 bits per weight](https://huggingface.co/turboderp/Phi-3-mini-128k-instruct-exl2/tree/5.0bpw)
[6.00 bits per weight](https://huggingface.co/turboderp/Phi-3-mini-128k-instruct-exl2/tree/6.0bpw)
[measurement.json](https://huggingface.co/turboderp/Phi-3-mini-128k-instruct-exl2/blob/main/measurement.json)