Instructions to use Xclbr7/Arcanum-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xclbr7/Arcanum-12b with Transformers:

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

pipe = pipeline("text-generation", model="Xclbr7/Arcanum-12b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Xclbr7/Arcanum-12b")
model = AutoModelForCausalLM.from_pretrained("Xclbr7/Arcanum-12b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Xclbr7/Arcanum-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xclbr7/Arcanum-12b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xclbr7/Arcanum-12b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Xclbr7/Arcanum-12b

SGLang

How to use Xclbr7/Arcanum-12b 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 "Xclbr7/Arcanum-12b" \
    --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": "Xclbr7/Arcanum-12b",
		"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 "Xclbr7/Arcanum-12b" \
        --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": "Xclbr7/Arcanum-12b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Xclbr7/Arcanum-12b with Docker Model Runner:
```
docker model run hf.co/Xclbr7/Arcanum-12b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Arcanum-12b 🧙‍♂️

Arcanum-12b is a merged large language model created by combining TheDrummer/Rocinante-12B-v1.1 and MarinaraSpaghetti/NemoMix-Unleashed-12B using a novel merging technique.

Model Details 📊

Developed by: Xclbr7
Model type: Causal Language Model
Language(s): English (primarily), may support other languages
License: MIT
Repository: https://huggingface.co/Xclbr7/Arcanum-12b

Model Architecture 🏗️

Base model: MarinaraSpaghetti/NemoMix-Unleashed-12B
Parameter count: ~12 billion
Architecture specifics: Transformer-based language model

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	20.48
IFEval (0-Shot)	29.07
BBH (3-Shot)	31.88
MATH Lvl 5 (4-Shot)	10.27
GPQA (0-shot)	9.40
MuSR (0-shot)	13.53
MMLU-PRO (5-shot)	28.74

Training & Merging 🔄

Arcanum-12b was created by merging two existing 12B models:

TheDrummer/Rocinante-12B-v1.1
- Density parameters: [1, 0.8, 0.6]
- Weight: 0.7
MarinaraSpaghetti/NemoMix-Unleashed-12B
- Density parameters: [0.5, 0.7, 0.9]
- Weight: 0.8

Merging method: Ties Additional parameters:

Normalization: True
Int8 mask: True
Data type: float16

Intended Use 🎯

Conversation with different personas.

Ethical Considerations 🤔

As a merged model based on existing language models, Arcanum-12b may inherit biases and limitations from its parent models. Users should be aware of potential biases in generated content and use the model responsibly.

Acknowledgments 🙏

We acknowledge the contributions of the original model creators:

TheDrummer for Rocinante-12B-v1.1
MarinaraSpaghetti for NemoMix-Unleashed-12B

Their work formed the foundation for Arcanum-12b.

Downloads last month: 13

Model tree for Xclbr7/Arcanum-12b

Finetunes

2 models

Quantizations

5 models

Spaces using Xclbr7/Arcanum-12b 6

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

29.070
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

31.880
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

10.270
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

9.400
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

13.530
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

28.740