cmh/phi-4_exl2

Phi-4 converted for ExLlamaV2

ExLlamaV2 is an inference library for running local LLMs on modern consumer GPUs.

	Quant type	File Size	Vram*
phi-4 hb8 3bpw	3 bits per weight	6.66 GB	10,3 GB
phi-4 hb8 4bpw	4 bits per weight	8.36 GB	11,9 GB
phi-4 hb8 5bpw	5 bits per weight	10.1 GB	13,5 GB
phi-4 hb8 6bpw	6 bits per weight	11.8 GB	15,1 GB
phi-4 hb8 7bpw	7 bits per weight	13.5 GB	16,7 GB
phi-4 hb8 8bpw	8 bits per weight	15.2 GB	18,2 GB

_{*approximate value at 16k context, FP16 cache.}

---

Phi-4 Model Card

Phi-4 Technical Report

Model Summary

Developers	Microsoft Research
Description	phi-4 is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning. phi-4 underwent a rigorous enhancement and alignment process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures
Architecture	14B parameters, dense decoder-only Transformer model
Context length	16384 tokens

Usage

Input Formats

Given the nature of the training data, phi-4 is best suited for prompts using the chat format as follows:

<|im_start|>system<|im_sep|>
You are a medieval knight and must provide explanations to modern people.<|im_end|>
<|im_start|>user<|im_sep|>
How should I explain the Internet?<|im_end|>
<|im_start|>assistant<|im_sep|>

With ExUI:

Add Phi-4 prompt format:

Edit/replace exui/backend/prompts.py with https://huggingface.co/cmh/phi-4_exl2/raw/main/backend/prompts.py