Instructions to use FPHam/Ebony_FicWriter_13b_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FPHam/Ebony_FicWriter_13b_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FPHam/Ebony_FicWriter_13b_GGUF",
	filename="Ebony_FicWriter_Q5_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 FPHam/Ebony_FicWriter_13b_GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FPHam/Ebony_FicWriter_13b_GGUF:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf FPHam/Ebony_FicWriter_13b_GGUF:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FPHam/Ebony_FicWriter_13b_GGUF:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf FPHam/Ebony_FicWriter_13b_GGUF:Q5_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 FPHam/Ebony_FicWriter_13b_GGUF:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf FPHam/Ebony_FicWriter_13b_GGUF:Q5_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 FPHam/Ebony_FicWriter_13b_GGUF:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FPHam/Ebony_FicWriter_13b_GGUF:Q5_K_M

Use Docker

docker model run hf.co/FPHam/Ebony_FicWriter_13b_GGUF:Q5_K_M

LM Studio
Jan
Ollama
How to use FPHam/Ebony_FicWriter_13b_GGUF with Ollama:
```
ollama run hf.co/FPHam/Ebony_FicWriter_13b_GGUF:Q5_K_M
```

Unsloth Studio new

How to use FPHam/Ebony_FicWriter_13b_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 FPHam/Ebony_FicWriter_13b_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 FPHam/Ebony_FicWriter_13b_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FPHam/Ebony_FicWriter_13b_GGUF to start chatting

Docker Model Runner
How to use FPHam/Ebony_FicWriter_13b_GGUF with Docker Model Runner:
```
docker model run hf.co/FPHam/Ebony_FicWriter_13b_GGUF:Q5_K_M
```

Lemonade

How to use FPHam/Ebony_FicWriter_13b_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FPHam/Ebony_FicWriter_13b_GGUF:Q5_K_M

Run and chat with the model

lemonade run user.Ebony_FicWriter_13b_GGUF-Q5_K_M

List all available models

lemonade list

Buy Enoby Ko-fi

Ebony FicWriter Introduction

"I don't know what you mean," Ebony replied innocently. "I just love writing stories for the fandom."

It was true enough; it wasn't as if she had ever tried to create anything original herself. Her prose style showed no sign of having matured over the years.

If anything, it was even more unashamedly purile than when she first started out, with every sentence dripping with the most lurid double entendres imaginable. Yet still she insisted on ploughing ahead, determined to cram into each and every story every single one of those ghastly Gothic clichés - not to mention assorted characters from the Wizarding World That Shall Not Be Named - regardless of whether they fitted or made any sense at all. And there was still that disturbing fixation with Draco Malfoy ...

"Ebony, darling?"

Her eyes widened. "What?" She flushed prettily.

"Well," I said, after a moment's deliberation. "You have improved your grammar slightly. Barely noticeably, but still ..."

"Grammar! What about my grammar? I never got no problem with my grammar!"

"Well, maybe not," I agreed, feeling vaguely guilty. "At least you've made an effort. So what you like to write about these days?" I changed the subject.

"Just stuff, really. I'm working on a new project right now. It's called 'The Unfortunate Lustfulness of Draco Malfoy.' Do you want me to read some of it to you?"

I shook my head quickly. "No, thank you. Sounds quite... not my style. But I hope you enjoy writing it."

"Oh, yes! Thank you. Well, I should probably get back to work then. Nice seeing you again, FP Ham!"

"Wait, wait," I said hurriedly. "What's your real name?"

"My real name? Oh, that's Staze.

And with a final smile, she disappeared through the doorway.

Enoby uses ALPACA instruct

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Write me a new episode for Star Trek crossover with Pride and Prejudice. Use first POV. 
 
### Response:

Example of Ebony's fanfic writing "style"

Downloads last month: 5

GGUF

Model size

13B params

Architecture

llama

Hardware compatibility

5-bit

Inference Providers NEW

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