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

Libraries

How to use dimsavva/phi4-noesis with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dimsavva/phi4-noesis",
	filename="phi4-noesis.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use dimsavva/phi4-noesis with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

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 dimsavva/phi4-noesis
# Run inference directly in the terminal:
./llama-cli -hf dimsavva/phi4-noesis

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 dimsavva/phi4-noesis
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dimsavva/phi4-noesis

Use Docker

docker model run hf.co/dimsavva/phi4-noesis

LM Studio
Jan
Ollama
How to use dimsavva/phi4-noesis with Ollama:
```
ollama run hf.co/dimsavva/phi4-noesis
```

Unsloth Studio new

How to use dimsavva/phi4-noesis 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 dimsavva/phi4-noesis 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 dimsavva/phi4-noesis to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use dimsavva/phi4-noesis with Docker Model Runner:
```
docker model run hf.co/dimsavva/phi4-noesis
```

Lemonade

How to use dimsavva/phi4-noesis with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dimsavva/phi4-noesis

Run and chat with the model

lemonade run user.phi4-noesis-{{QUANT_TAG}}

List all available models

lemonade list

Please share fine tuning approach, tool, and if possible data sets

by upmittal - opened Feb 12, 2025

Discussion

upmittal

Feb 12, 2025

Dimitrios Savva can you also let us k ow how you created a training data set (if possible open source that as well)? Which method you used to fine tune phi 4. Thanks in advance.

dimsavva

Owner Feb 12, 2025

I will do. Please expect a full tutorial in the next few days.

upmittal

Feb 13, 2025

Thanks, in case yu can add the reasoning data set youused or even partial set and training file (I am assuming you used unsloth , it wil be a great help.

I can collaborate with you on getting data set enhanced or updated. My interest is in converting old PL/SQl code to c#.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment