Instructions to use PatronusAI/glider-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PatronusAI/glider-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="PatronusAI/glider-gguf",
	filename="glider_BF16.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 PatronusAI/glider-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PatronusAI/glider-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf PatronusAI/glider-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 PatronusAI/glider-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf PatronusAI/glider-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 PatronusAI/glider-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf PatronusAI/glider-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 PatronusAI/glider-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PatronusAI/glider-gguf:Q4_K_M

Use Docker

docker model run hf.co/PatronusAI/glider-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use PatronusAI/glider-gguf with Ollama:
```
ollama run hf.co/PatronusAI/glider-gguf:Q4_K_M
```

Unsloth Studio new

How to use PatronusAI/glider-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 PatronusAI/glider-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 PatronusAI/glider-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PatronusAI/glider-gguf to start chatting

Docker Model Runner
How to use PatronusAI/glider-gguf with Docker Model Runner:
```
docker model run hf.co/PatronusAI/glider-gguf:Q4_K_M
```

Lemonade

How to use PatronusAI/glider-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PatronusAI/glider-gguf:Q4_K_M

Run and chat with the model

lemonade run user.glider-gguf-Q4_K_M

List all available models

lemonade list

Available GGUF versions for the PatronusAI/glider model: [BF16, Q8_0, Q5_K_M, Q4_K_M]

How to load your desired quantized model:

Select the appropraite GGUF quantization from the available list above
Run the following code:

from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("PatronusAI/glider-gguf", gguf_file="glider_{version_from_list}.gguf")

For loading the Q8_0 version, this script will change to:

from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("PatronusAI/glider-gguf", gguf_file="glider_Q8_0.gguf")

For any issues or questions, reach out to Darshan Deshpande or Rebecca Qian

Downloads last month: 37

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for PatronusAI/glider-gguf

Base model

microsoft/Phi-3.5-mini-instruct

Finetuned

PatronusAI/glider

Quantized

(1)

this model