metadata
tags:
- uqff
- mistral.rs
base_model: microsoft/Phi-3.5-mini-instruct
base_model_relation: quantized
microsoft/Phi-3.5-mini-instruct
, UQFF quantization
Run with mistral.rs. Documentation: UQFF docs.
- Flexible ๐: Multiple quantization formats in one file format with one framework to run them all.
- Reliable ๐: Compatibility ensured with embedded and checked semantic versioning information from day 1.
- Easy ๐ค: Download UQFF models easily and quickly from Hugging Face, or use a local file.
- Customizable ๐ ๏ธ: Make and publish your own UQFF files in minutes.
Files
Name | Quantization type(s) | Example |
---|---|---|
phi3.5-mini-instruct-q4k.uqff | Q4K | ./mistralrs-server plain -m microsoft/Phi-3.5-mini-instruct --from-uqff EricB/Phi-3.5-mini-instruct-UQFF/phi3.5-mini-instruct-q4k.uqff |
phi3.5-mini-instruct-hqq4.uqff | HQQ4 | ./mistralrs-server plain -m microsoft/Phi-3.5-mini-instruct --from-uqff EricB/Phi-3.5-mini-instruct-UQFF/phi3.5-mini-instruct-hqq4.uqff |