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

Libraries

How to use AbstractPhil/clips with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AbstractPhil/clips",
	filename="t5-v1_1-xxl-encoder-Q3_K_M.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 AbstractPhil/clips with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AbstractPhil/clips:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AbstractPhil/clips:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/AbstractPhil/clips:Q4_K_M

LM Studio
Jan
Ollama
How to use AbstractPhil/clips with Ollama:
```
ollama run hf.co/AbstractPhil/clips:Q4_K_M
```

Unsloth Studio new

How to use AbstractPhil/clips 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 AbstractPhil/clips 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 AbstractPhil/clips to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use AbstractPhil/clips with Docker Model Runner:
```
docker model run hf.co/AbstractPhil/clips:Q4_K_M
```

Lemonade

How to use AbstractPhil/clips with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AbstractPhil/clips:Q4_K_M

Run and chat with the model

lemonade run user.clips-Q4_K_M

List all available models

lemonade list

What are these latest NAI epsilon clips for?

by Kutches - opened Jun 24, 2025

Discussion

Kutches

Jun 24, 2025

It would be nice if you describe some of these clips it would be used more if people knew what they were for

Kutches changed discussion title from What are these latest epsilon clips for? to What are these latest NAI epsilon clips for? Jun 24, 2025

AbstractPhil

Owner Jun 24, 2025

•

edited Jun 24, 2025

They are pulled from the SDXL-NAI epsilon v11 and I'm about to upload shunts for them.
These are NoobXL clips.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment