Edit model card

Exllama v2 Quantizations of Phi-3-mini-128k-instruct

Using turboderp's ExLlamaV2 v0.0.20 for quantization.

The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Conversion was done using the default calibration dataset.

Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.

Original model: https://huggingface.co/microsoft/Phi-3-mini-128k-instruct

8.0 bits per weight

6.5 bits per weight

5.0 bits per weight

4.25 bits per weight

3.5 bits per weight

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Phi-3-mini-128k-instruct-exl2

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

To download the main (only useful if you only care about measurement.json) branch to a folder called Phi-3-mini-128k-instruct-exl2:

mkdir Phi-3-mini-128k-instruct-exl2
huggingface-cli download bartowski/Phi-3-mini-128k-instruct-exl2 --local-dir Phi-3-mini-128k-instruct-exl2 --local-dir-use-symlinks False

To download from a different branch, add the --revision parameter:

Linux:

mkdir Phi-3-mini-128k-instruct-exl2-6_5
huggingface-cli download bartowski/Phi-3-mini-128k-instruct-exl2 --revision 6_5 --local-dir Phi-3-mini-128k-instruct-exl2-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

mkdir Phi-3-mini-128k-instruct-exl2-6.5
huggingface-cli download bartowski/Phi-3-mini-128k-instruct-exl2 --revision 6_5 --local-dir Phi-3-mini-128k-instruct-exl2-6.5 --local-dir-use-symlinks False
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Examples
Unable to determine this model's library. Check the docs .