Instructions to use sayhan/phi-2-super-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sayhan/phi-2-super-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sayhan/phi-2-super-GGUF",
	filename="phi-2-super.Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use sayhan/phi-2-super-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sayhan/phi-2-super-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf sayhan/phi-2-super-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sayhan/phi-2-super-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf sayhan/phi-2-super-GGUF: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 sayhan/phi-2-super-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sayhan/phi-2-super-GGUF: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 sayhan/phi-2-super-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sayhan/phi-2-super-GGUF:Q4_K_M

Use Docker

docker model run hf.co/sayhan/phi-2-super-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use sayhan/phi-2-super-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sayhan/phi-2-super-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sayhan/phi-2-super-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sayhan/phi-2-super-GGUF:Q4_K_M

Ollama
How to use sayhan/phi-2-super-GGUF with Ollama:
```
ollama run hf.co/sayhan/phi-2-super-GGUF:Q4_K_M
```

Unsloth Studio new

How to use sayhan/phi-2-super-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 sayhan/phi-2-super-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 sayhan/phi-2-super-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sayhan/phi-2-super-GGUF to start chatting

Docker Model Runner
How to use sayhan/phi-2-super-GGUF with Docker Model Runner:
```
docker model run hf.co/sayhan/phi-2-super-GGUF:Q4_K_M
```

Lemonade

How to use sayhan/phi-2-super-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sayhan/phi-2-super-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.phi-2-super-GGUF-Q4_K_M

List all available models

lemonade list

Phi-2 Super (SFT + cDPO)

Model creator: Anton Bacaj
Original model: Phi-2 Super

Description

This repo contains GGUF format model files for abacaj's Phi-2 Super

Quantization types

Since the model is relatively very small, I recommend the larger quantizations.

quantization method	bits	description	recommended
Q2_K	2	smallest, significant quality loss	❌
Q3_K_S	3	very small, high quality loss	❌
Q3_K_M	3	very small, high quality loss	❌
Q3_K_L	3	small, substantial quality loss	❌
Q4_0	4	legacy; small, very high quality loss	❌
Q4_K_M	4	medium, balanced quality	❌
Q5_0	5	legacy; medium, balanced quality	❌
Q5_K_S	5	large, low quality loss	✅
Q5_K_M	5	large, very low quality loss	✅
Q6_K	6	very large, extremely low quality loss	❌
Q8_0	8	very large, extremely low quality loss	❌
FP16	16	enormous, negligible quality loss	❌

Phi-2-super (SFT + cDPO)

Base Model: microsoft/phi-2

Chat template

The model uses the same chat template as found in Mistral instruct models:

text = "<|endoftext|>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!<|endoftext|> "
"[INST] Do you have mayonnaise recipes? [/INST]"

MT-bench / heval

Downloads last month: 173

GGUF

Model size

3B params

Architecture

phi2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant