Hugging Face's logo

microsoft
/
Phi-3-mini-4k-instruct

Text Generation
Transformers
Safetensors
English
French
phi3
nlp
code
conversational
custom_code
text-generation-inference
Model card Files Community
100

Quantized

#13
by wrosko - opened
Discussion
wrosko

The paper suggests 4-bit quantization, will Microsoft release the quantized version?

nguyenbh
 Microsoft org

There are quantized models here:
https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-onnx
https://huggingface.co/microsoft/Phi-3-mini-128k-instruct-onnx
https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf

nguyenbh changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment