Instructions to use nisten/phi3-medium-128k-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nisten/phi3-medium-128k-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nisten/phi3-medium-128k-gguf",
	filename="13phi128kf16.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 nisten/phi3-medium-128k-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nisten/phi3-medium-128k-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf nisten/phi3-medium-128k-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nisten/phi3-medium-128k-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf nisten/phi3-medium-128k-gguf:F16

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 nisten/phi3-medium-128k-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf nisten/phi3-medium-128k-gguf:F16

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 nisten/phi3-medium-128k-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nisten/phi3-medium-128k-gguf:F16

Use Docker

docker model run hf.co/nisten/phi3-medium-128k-gguf:F16

LM Studio
Jan
Ollama
How to use nisten/phi3-medium-128k-gguf with Ollama:
```
ollama run hf.co/nisten/phi3-medium-128k-gguf:F16
```

Unsloth Studio new

How to use nisten/phi3-medium-128k-gguf 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 nisten/phi3-medium-128k-gguf 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 nisten/phi3-medium-128k-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nisten/phi3-medium-128k-gguf to start chatting

Docker Model Runner
How to use nisten/phi3-medium-128k-gguf with Docker Model Runner:
```
docker model run hf.co/nisten/phi3-medium-128k-gguf:F16
```

Lemonade

How to use nisten/phi3-medium-128k-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nisten/phi3-medium-128k-gguf:F16

Run and chat with the model

lemonade run user.phi3-medium-128k-gguf-F16

List all available models

lemonade list

GGUF and imatrix files of https://huggingface.co/microsoft/Phi-3-medium-128k-instruct

Chat Format

<|user|>\nQuestion <|end|>\n<|assistant|>

For example:

<|user|>
How to explain Internet for a medieval knight?<|end|>
<|assistant|>

More uploading and perplexity benchmarks to be posted soon. Long context config may change, only tested up to 4k so far.

Cheers, Nisten

Downloads last month: 35

GGUF

Model size

14B params

Architecture

phi3

Hardware compatibility

16-bit

View +4 variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for nisten/phi3-medium-128k-gguf

Base model

microsoft/Phi-3-medium-128k-instruct

Quantized

(75)

this model