Instructions to use cloudyu/Phoenix_DPO_60B_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cloudyu/Phoenix_DPO_60B_gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cloudyu/Phoenix_DPO_60B_gguf",
	filename="cloudyu_Phoenix_DPO_60B.Q3_K_XS.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cloudyu/Phoenix_DPO_60B_gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cloudyu/Phoenix_DPO_60B_gguf:Q4_0
# Run inference directly in the terminal:
llama-cli -hf cloudyu/Phoenix_DPO_60B_gguf:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cloudyu/Phoenix_DPO_60B_gguf:Q4_0
# Run inference directly in the terminal:
llama-cli -hf cloudyu/Phoenix_DPO_60B_gguf:Q4_0

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 cloudyu/Phoenix_DPO_60B_gguf:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf cloudyu/Phoenix_DPO_60B_gguf:Q4_0

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 cloudyu/Phoenix_DPO_60B_gguf:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cloudyu/Phoenix_DPO_60B_gguf:Q4_0

Use Docker

docker model run hf.co/cloudyu/Phoenix_DPO_60B_gguf:Q4_0

LM Studio
Jan
Ollama
How to use cloudyu/Phoenix_DPO_60B_gguf with Ollama:
```
ollama run hf.co/cloudyu/Phoenix_DPO_60B_gguf:Q4_0
```

Unsloth Studio new

How to use cloudyu/Phoenix_DPO_60B_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 cloudyu/Phoenix_DPO_60B_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 cloudyu/Phoenix_DPO_60B_gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cloudyu/Phoenix_DPO_60B_gguf to start chatting

Docker Model Runner
How to use cloudyu/Phoenix_DPO_60B_gguf with Docker Model Runner:
```
docker model run hf.co/cloudyu/Phoenix_DPO_60B_gguf:Q4_0
```

Lemonade

How to use cloudyu/Phoenix_DPO_60B_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cloudyu/Phoenix_DPO_60B_gguf:Q4_0

Run and chat with the model

lemonade run user.Phoenix_DPO_60B_gguf-Q4_0

List all available models

lemonade list

Description

This repo contains GGUF format model files for cloudyu/Phoenix_DPO_60B.

About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

How to run GGUF with llama.cpp on an A10 (24G vram)

   git clone https://github.com/ggerganov/llama.cpp.git
   cd llama.cpp/
   make LLAMA_CUBLAS=1
   ./main --model ./cloudyu_Phoenix_DPO_60B.Q3_K_XS.gguf -p "what is biggest animal?" -i -ngl 36

Downloads last month: 42

GGUF

Model size

61B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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