Instructions to use rAIfle/Luca-MN-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rAIfle/Luca-MN-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="rAIfle/Luca-MN-bf16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rAIfle/Luca-MN-bf16")
model = AutoModelForCausalLM.from_pretrained("rAIfle/Luca-MN-bf16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rAIfle/Luca-MN-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rAIfle/Luca-MN-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rAIfle/Luca-MN-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rAIfle/Luca-MN-bf16

SGLang

How to use rAIfle/Luca-MN-bf16 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 "rAIfle/Luca-MN-bf16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rAIfle/Luca-MN-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "rAIfle/Luca-MN-bf16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rAIfle/Luca-MN-bf16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use rAIfle/Luca-MN-bf16 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 rAIfle/Luca-MN-bf16 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 rAIfle/Luca-MN-bf16 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rAIfle/Luca-MN-bf16 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="rAIfle/Luca-MN-bf16",
    max_seq_length=2048,
)

Docker Model Runner
How to use rAIfle/Luca-MN-bf16 with Docker Model Runner:
```
docker model run hf.co/rAIfle/Luca-MN-bf16
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Luca-MN-bf16

This thing was just intended as an experiment but it turned out quite good. I had it both name and prompt imagegen for itself.

Created by running a high-r LoRA-pass over Nemo-Base with 2 epochs of some RP data, then a low-r pass with 0.5 epochs of the c2-data, then 3 epochs of DPO using jondurbin/gutenberg-dpo-v0.1.

Prompting

Use the Mistral V3-Tekken context- and instruct-templates. Temperature at about 1.25 seems to be the sweet spot, with either MinP at 0.05 or TopP at 0.9. DRY/Smoothing etc depending on your preference.

Quantized versions

iMat GGUFs, courtesy of the Quant-Cartel

Downloads last month: 7

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for rAIfle/Luca-MN-bf16

Base model

unsloth/Mistral-Nemo-Base-2407-bnb-4bit

Finetuned

(55)

this model

Quantizations

2 models