Instructions to use PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed with Pruna AI:

from pruna import PrunaModel
model = PrunaModel.from_pretrained("PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed: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 PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed: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 PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed:Q4_K_M

Use Docker

docker model run hf.co/PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed:Q4_K_M

LM Studio
Jan
Ollama
How to use PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed with Ollama:
```
ollama run hf.co/PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed with Docker Model Runner:
```
docker model run hf.co/PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed:Q4_K_M
```

Lemonade

How to use PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed:Q4_K_M

Run and chat with the model

lemonade run user.Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed-Q4_K_M

List all available models

lemonade list

Atomic Chat

New discussion

Resources

View closed (2)

Why is the generated content always the same when I use this model?

#7 opened about 2 years ago by

LiMuyi

Phi 3 tokenizer_config has been updated upstream

#6 opened over 2 years ago by

smcleod

Mistake in readme instructions

🤝 2

#5 opened over 2 years ago by

adamkdean

gibberish results when context is greater 2048

#4 opened over 2 years ago by

Bakanayatsu

Do they work with ollama? How was the conversion done for 128K, llama.cpp/convert.py complains about ROPE.

#2 opened over 2 years ago by

BigDeeper