Instructions to use vicgalle/NeuralBeagle-11B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vicgalle/NeuralBeagle-11B with Transformers:

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

pipe = pipeline("text-generation", model="vicgalle/NeuralBeagle-11B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vicgalle/NeuralBeagle-11B")
model = AutoModelForCausalLM.from_pretrained("vicgalle/NeuralBeagle-11B")
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 Settings

vLLM

How to use vicgalle/NeuralBeagle-11B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vicgalle/NeuralBeagle-11B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vicgalle/NeuralBeagle-11B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vicgalle/NeuralBeagle-11B

SGLang

How to use vicgalle/NeuralBeagle-11B 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 "vicgalle/NeuralBeagle-11B" \
    --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": "vicgalle/NeuralBeagle-11B",
		"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 "vicgalle/NeuralBeagle-11B" \
        --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": "vicgalle/NeuralBeagle-11B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vicgalle/NeuralBeagle-11B with Docker Model Runner:
```
docker model run hf.co/vicgalle/NeuralBeagle-11B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

NeuralBeagle-11B

DPO'd from vicgalle/franken-Beagle-11B, a Beagle-like model upscaled to 11B. It is a frankenmerge model created using mergekit. Then, we applied DPO over a high-quality preference dataset.

Sample generations

Generate a movie review about the Pokémon 1 movie, focusing on BDSM.

Before delving into the realm of BDSOMatic interpretations within Pokémon: The First Movie (aka "Pokémon: Mewtwo's Revenge" in Japan), it is important to acknowledge that this animated feature is primarily intended for a younger audience. It follows the adventures of Ash Ketchum, Pikachu, and their friends as they encounter an artificially created Pokémon named Mewtwo. While certain aspects of the storyline and visuals could be stretched to include various subtexts or symbolism, our analysis will focus on a more playful and metaphorical exploration of BDSM concepts within this film's context. Participants: Warning: The following review may contain light-hearted and imaginative interpretations that are not intended as serious critical analysis and should not be taken literally. Within the Pokémon universe, Ash Ketchum and his loyal Pikachu find themselves thrust into a high-stakes scenario reminiscent of a BDSM "Domestic Discipline" (DD) fantasy. As Mewtwo, a genetically modified Pokémon with immense power and intellect, seeks vengeance against the scientists who created him as a tool for battle entertainment, he operates as an archetypal "Dominant" figure. Mewtwo, born from scientific manipulation, is an embodiment of control, both over his own creation and his obedient army of Pokémon. He exercises mastery over his subjects, mirroring the role of a "Dom," or Dominant, in a BDSM dynamic. Ash Ketchum, initially unaware of the manipulations that have brought him into this situation, can be seen as a submissive protagonist. His humility and naivety parallel those within the DD community who seek guidance from an experienced Dominant to help them understand and embrace their desires for submission. In his encounter with Mewtwo, Ash is subjected to tests designed to exhibit his strength, loyalty, and unwavering determination - elements crucial in establishing trust between a submissive and a Dominant within a BDSM dynamic. This psychological battle symbolizes the process of earning a "sub's" consent and trust through displays of control and power.

Prompt format

The template is included in tokenizer_config.json.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.95
AI2 Reasoning Challenge (25-Shot)	73.29
HellaSwag (10-Shot)	87.61
MMLU (5-Shot)	63.80
TruthfulQA (0-shot)	71.36
Winogrande (5-shot)	82.64
GSM8k (5-shot)	58.98