Instructions to use Sweaterdog/Andy-4-base-DEPRECATED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sweaterdog/Andy-4-base-DEPRECATED with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Sweaterdog/Andy-4-base-DEPRECATED",
	filename="Andy-4-preview.F16.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 Sweaterdog/Andy-4-base-DEPRECATED with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Sweaterdog/Andy-4-base-DEPRECATED:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Sweaterdog/Andy-4-base-DEPRECATED:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Sweaterdog/Andy-4-base-DEPRECATED:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Sweaterdog/Andy-4-base-DEPRECATED: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 Sweaterdog/Andy-4-base-DEPRECATED:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Sweaterdog/Andy-4-base-DEPRECATED: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 Sweaterdog/Andy-4-base-DEPRECATED:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Sweaterdog/Andy-4-base-DEPRECATED:Q4_K_M

Use Docker

docker model run hf.co/Sweaterdog/Andy-4-base-DEPRECATED:Q4_K_M

LM Studio
Jan
Ollama
How to use Sweaterdog/Andy-4-base-DEPRECATED with Ollama:
```
ollama run hf.co/Sweaterdog/Andy-4-base-DEPRECATED:Q4_K_M
```

Unsloth Studio new

How to use Sweaterdog/Andy-4-base-DEPRECATED 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 Sweaterdog/Andy-4-base-DEPRECATED 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 Sweaterdog/Andy-4-base-DEPRECATED to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Sweaterdog/Andy-4-base-DEPRECATED to start chatting

Docker Model Runner
How to use Sweaterdog/Andy-4-base-DEPRECATED with Docker Model Runner:
```
docker model run hf.co/Sweaterdog/Andy-4-base-DEPRECATED:Q4_K_M
```

Lemonade

How to use Sweaterdog/Andy-4-base-DEPRECATED with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sweaterdog/Andy-4-base-DEPRECATED:Q4_K_M

Run and chat with the model

lemonade run user.Andy-4-base-DEPRECATED-Q4_K_M

List all available models

lemonade list

Sweaterdog commited on Apr 2, 2025

Commit

84da72c

verified ·

1 Parent(s): ea8d8c8

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -31,6 +31,7 @@ This training regimen, coupled with advanced techniques like manual learning rat
 # How to install
 On Huggingface, press the `Use this model` dropdown menu, and choose `Ollama`, then in the drop down menu, choose your quantization, following this GPU VRAM chart:
 *All of these values assume a context window size of 8192 or less*
 ```
 F16 = 20+ GB

 # How to install
 On Huggingface, press the `Use this model` dropdown menu, and choose `Ollama`, then in the drop down menu, choose your quantization, following this GPU VRAM chart:
 *All of these values assume a context window size of 8192 or less*
 ```
 F16 = 20+ GB