Instructions to use ontocord/Felix-8B-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ontocord/Felix-8B-v2 with Transformers:

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

pipe = pipeline("text-generation", model="ontocord/Felix-8B-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ontocord/Felix-8B-v2")
model = AutoModelForCausalLM.from_pretrained("ontocord/Felix-8B-v2", device_map="auto")
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 ontocord/Felix-8B-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ontocord/Felix-8B-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ontocord/Felix-8B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ontocord/Felix-8B-v2

SGLang

How to use ontocord/Felix-8B-v2 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 "ontocord/Felix-8B-v2" \
    --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": "ontocord/Felix-8B-v2",
		"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 "ontocord/Felix-8B-v2" \
        --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": "ontocord/Felix-8B-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ontocord/Felix-8B-v2 with Docker Model Runner:
```
docker model run hf.co/ontocord/Felix-8B-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

April 17, 2024

Felix-8B-v2: A model built with lawfulness alignment

Felix-8B-v2 is an experimental language model developed by Ontocord.ai, specializing in addressing lawfulness concerns under the Biden-Harris Executive Order on AI and the principles of the EU AI Act. This model has achieved one of the highest scores on the TruthfulQA benchmark compared to models of its size, showcasing its exceptional performance in providing accurate and reliable responses. Felix-8B-v2 is experimental and a research work product and a DPO reinforcement learning version of ontocord/sft-4e-exp2 which in turn is a fine-tuned version of TencentARC/Mistral_Pro_8B_v0.1. Felix-8B was DPO trained on our synthetically generated dataset Auto Redteam Triplets (ART): a synthetic dataset to perform reinforcement learning redteaming for the EU AI Act and Biden-Harris AI Executive Order concerns.

This model is exactly the same as Felix-8B except we modified the </s> and <s> tags of the original Felix-8b DPO model to fix the issue of being too verbose.

Please give feedback in the Community section. If you find any issues please let us know in the Community section so we can improve the model.

Model Description

Felix-8B is an 8 billion parameter language model trained using Ontocord.ai's proprietary auto-purpleteaming technique. The model has been fine-tuned and optimized using synthetic data, with the goal of improving its robustness and ability to handle a wide range of tasks while maintaining a strong focus on safety and truthfulness.

Downloads last month: 5

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for ontocord/Felix-8B-v2

Quantizations

1 model