Instructions to use Gryphe/Various-Quants with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gryphe/Various-Quants with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Gryphe/Various-Quants",
	filename="pantheon-instruct-l3-8b.q6_K.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 Gryphe/Various-Quants with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Gryphe/Various-Quants:Q6_K
# Run inference directly in the terminal:
llama-cli -hf Gryphe/Various-Quants:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Gryphe/Various-Quants:Q6_K
# Run inference directly in the terminal:
llama-cli -hf Gryphe/Various-Quants:Q6_K

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 Gryphe/Various-Quants:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf Gryphe/Various-Quants:Q6_K

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 Gryphe/Various-Quants:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Gryphe/Various-Quants:Q6_K

Use Docker

docker model run hf.co/Gryphe/Various-Quants:Q6_K

LM Studio
Jan
Ollama
How to use Gryphe/Various-Quants with Ollama:
```
ollama run hf.co/Gryphe/Various-Quants:Q6_K
```

Unsloth Studio new

How to use Gryphe/Various-Quants 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 Gryphe/Various-Quants 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 Gryphe/Various-Quants to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Gryphe/Various-Quants to start chatting

Docker Model Runner
How to use Gryphe/Various-Quants with Docker Model Runner:
```
docker model run hf.co/Gryphe/Various-Quants:Q6_K
```

Lemonade

How to use Gryphe/Various-Quants with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Gryphe/Various-Quants:Q6_K

Run and chat with the model

lemonade run user.Various-Quants-Q6_K

List all available models

lemonade list

A repo to store various quants of models, for convenient sharing and testing of freshly produced merges. Try at your own risk! Files may be deleted over time, usually due to them being released properly.

Don't forget to check my repo for all my other models!

Downloads last month: 115

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

6-bit

Inference Providers NEW

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