bartowski
/

Phi-3-medium-128k-instruct-GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (1)

Correct promt format is crucial.

#5 opened 3 months ago by

Phi-3 models must be re-converted after recent llama.cpp commit

#4 opened 4 months ago by

Quantization suggestion

#3 opened 5 months ago by

4k versions load and work in Koboldcpp, but the 128k versions don't.

#1 opened 6 months ago by