Instructions to use 922-CA/Llama-3-natsuki-ddlc-8b-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 922-CA/Llama-3-natsuki-ddlc-8b-v1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="922-CA/Llama-3-natsuki-ddlc-8b-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("922-CA/Llama-3-natsuki-ddlc-8b-v1")
model = AutoModelForCausalLM.from_pretrained("922-CA/Llama-3-natsuki-ddlc-8b-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 922-CA/Llama-3-natsuki-ddlc-8b-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "922-CA/Llama-3-natsuki-ddlc-8b-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "922-CA/Llama-3-natsuki-ddlc-8b-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/922-CA/Llama-3-natsuki-ddlc-8b-v1

SGLang

How to use 922-CA/Llama-3-natsuki-ddlc-8b-v1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "922-CA/Llama-3-natsuki-ddlc-8b-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "922-CA/Llama-3-natsuki-ddlc-8b-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "922-CA/Llama-3-natsuki-ddlc-8b-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "922-CA/Llama-3-natsuki-ddlc-8b-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use 922-CA/Llama-3-natsuki-ddlc-8b-v1 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 922-CA/Llama-3-natsuki-ddlc-8b-v1 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 922-CA/Llama-3-natsuki-ddlc-8b-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 922-CA/Llama-3-natsuki-ddlc-8b-v1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="922-CA/Llama-3-natsuki-ddlc-8b-v1",
    max_seq_length=2048,
)

Docker Model Runner
How to use 922-CA/Llama-3-natsuki-ddlc-8b-v1 with Docker Model Runner:
```
docker model run hf.co/922-CA/Llama-3-natsuki-ddlc-8b-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3-Natsuki-DDLC-8b-v1

Model fine-tuned for Natsuki character from DDLC
Base: LLaMA-3
GGUFs

USAGE

For best results: replace "Human" and "Assistant" with "Player" and "Natsuki" like so:

\nPlayer: (prompt)\nNatsuki:

HYPERPARAMS

Trained for 1 epoch
rank: 32
lora alpha: 32
lora dropout: 0
lr: 2e-4
batch size: 2
grad steps: 4

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

WARNINGS AND DISCLAIMERS

This model is meant to closely reflect the characteristics of Natsuki. Despite this, there is always the chance that "Natsuki" will hallucinate and get information about herself wrong or act out of character.

Finally, this model is not guaranteed to output aligned or safe outputs, use at your own risk.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	62.02
AI2 Reasoning Challenge (25-Shot)	60.32
HellaSwag (10-Shot)	80.99
MMLU (5-Shot)	64.75
TruthfulQA (0-shot)	45.41
Winogrande (5-shot)	78.77
GSM8k (5-shot)	41.85