Instructions to use calcuis/phi4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use calcuis/phi4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="calcuis/phi4",
	filename="phi4-f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use calcuis/phi4 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf calcuis/phi4:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf calcuis/phi4:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf calcuis/phi4:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf calcuis/phi4:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf calcuis/phi4:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf calcuis/phi4:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf calcuis/phi4:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf calcuis/phi4:Q4_K_M

Use Docker

docker model run hf.co/calcuis/phi4:Q4_K_M

LM Studio
Jan

vLLM

How to use calcuis/phi4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "calcuis/phi4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "calcuis/phi4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/calcuis/phi4:Q4_K_M

Ollama
How to use calcuis/phi4 with Ollama:
```
ollama run hf.co/calcuis/phi4:Q4_K_M
```

Unsloth Studio

How to use calcuis/phi4 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for calcuis/phi4 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for calcuis/phi4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for calcuis/phi4 to start chatting

Docker Model Runner
How to use calcuis/phi4 with Docker Model Runner:
```
docker model run hf.co/calcuis/phi4:Q4_K_M
```

Lemonade

How to use calcuis/phi4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull calcuis/phi4:Q4_K_M

Run and chat with the model

lemonade run user.phi4-Q4_K_M

List all available models

lemonade list

calcuis commited on Jan 22, 2025

Commit

b8917cb

verified ·

1 Parent(s): 3bfbdca

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -17

README.md CHANGED Viewed

@@ -19,20 +19,3 @@ tags:
 ## reference
 - base model: microsoft/[phi-4](https://huggingface.co/microsoft/phi-4)
 - gguf-connector ([pypi](https://pypi.org/project/gguf-connector/)|[reop](https://github.com/calcuis/gguf-connector))
-## appendix
-|-------------------------|-------------------------------------------------------------------------------|
-| **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.<br><br>`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                          |
-| **Inputs**              | Text, best suited for prompts in the chat format                              |
-| **Context length**      | 16K tokens                                                                    |
-| **GPUs**                | 1920 H100-80G                                                                 |
-| **Training time**       | 21 days                                                                       |
-| **Training data**       | 9.8T tokens                                                                   |
-| **Outputs**             | Generated text in response to input                                           |
-| **Dates**               | October 2024 – November 2024                                                  |
-| **Status**              | Static model trained on an offline dataset with cutoff dates of June 2024 and earlier for publicly available data                                                                               |
-| **Release date**        | December 12, 2024                                                             |
-| **License**             | MIT                                                                         |

 ## reference
 - base model: microsoft/[phi-4](https://huggingface.co/microsoft/phi-4)
 - gguf-connector ([pypi](https://pypi.org/project/gguf-connector/)|[reop](https://github.com/calcuis/gguf-connector))