Instructions to use CMM7590/Lilith_AI_135M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CMM7590/Lilith_AI_135M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="CMM7590/Lilith_AI_135M",
	filename="Lilith_AI_135M_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 CMM7590/Lilith_AI_135M with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CMM7590/Lilith_AI_135M:F16
# Run inference directly in the terminal:
llama-cli -hf CMM7590/Lilith_AI_135M:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf CMM7590/Lilith_AI_135M:F16
# Run inference directly in the terminal:
llama-cli -hf CMM7590/Lilith_AI_135M:F16

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 CMM7590/Lilith_AI_135M:F16
# Run inference directly in the terminal:
./llama-cli -hf CMM7590/Lilith_AI_135M:F16

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 CMM7590/Lilith_AI_135M:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf CMM7590/Lilith_AI_135M:F16

Use Docker

docker model run hf.co/CMM7590/Lilith_AI_135M:F16

LM Studio
Jan
Ollama
How to use CMM7590/Lilith_AI_135M with Ollama:
```
ollama run hf.co/CMM7590/Lilith_AI_135M:F16
```

Unsloth Studio new

How to use CMM7590/Lilith_AI_135M 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 CMM7590/Lilith_AI_135M 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 CMM7590/Lilith_AI_135M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for CMM7590/Lilith_AI_135M to start chatting

Docker Model Runner
How to use CMM7590/Lilith_AI_135M with Docker Model Runner:
```
docker model run hf.co/CMM7590/Lilith_AI_135M:F16
```

Lemonade

How to use CMM7590/Lilith_AI_135M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull CMM7590/Lilith_AI_135M:F16

Run and chat with the model

lemonade run user.Lilith_AI_135M-F16

List all available models

lemonade list

Lilith AI

An LLM trained to act like Lilith from The NOexistenceN of you AND me.
An 8B parameter version can be found here: CMM7590/Lilith_AI_8B

This is an ultra low parameter model and may not work correctly!

About

This model is a LoRA fine-tuned LLM based on the HuggingFaceTB/SmolLM2-135M-Instruct base model. It has been trained on lines directly extracted from the original game to simulate the personality and speech patterns of Lilith.

Works well on mobile devices, though don't expect too much.

The cloud-hosted model can be found here: lilith.nullexistence.net

Folder & File Overview

System Prompt.txt: A system prompt tailored specifically for this model.
Lilith_AI_135M_Q8_0.gguf: The Q8_0 model file.
Lilith_AI_135M_F16.gguf: The F16 model file.

License

You are free to use, share, and adapt the model, but you must give appropriate credit to C.M.M. for training the model and this project.

Disclaimer

This model uses the character Lilith from The NOexistenceN series. This project is fan-made and not affiliated with, endorsed by, or sponsored by the original creators or copyright holders. All intellectual property related to the character belongs to the original copyright holders. Use of this model is for personal, educational, or research purposes only.

Downloads last month: 16

GGUF

Model size

0.1B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

Inference Providers NEW

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

Model tree for CMM7590/Lilith_AI_135M

Base model

HuggingFaceTB/SmolLM2-135M

Quantized

HuggingFaceTB/SmolLM2-135M-Instruct

Quantized

(101)

this model