Instructions to use DeepDream2045/NeuralDaredevil-7b-exl2-8bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepDream2045/NeuralDaredevil-7b-exl2-8bpw with Transformers:

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

pipe = pipeline("text-generation", model="DeepDream2045/NeuralDaredevil-7b-exl2-8bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeepDream2045/NeuralDaredevil-7b-exl2-8bpw")
model = AutoModelForCausalLM.from_pretrained("DeepDream2045/NeuralDaredevil-7b-exl2-8bpw")
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 DeepDream2045/NeuralDaredevil-7b-exl2-8bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepDream2045/NeuralDaredevil-7b-exl2-8bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepDream2045/NeuralDaredevil-7b-exl2-8bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DeepDream2045/NeuralDaredevil-7b-exl2-8bpw

SGLang

How to use DeepDream2045/NeuralDaredevil-7b-exl2-8bpw 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 "DeepDream2045/NeuralDaredevil-7b-exl2-8bpw" \
    --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": "DeepDream2045/NeuralDaredevil-7b-exl2-8bpw",
		"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 "DeepDream2045/NeuralDaredevil-7b-exl2-8bpw" \
        --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": "DeepDream2045/NeuralDaredevil-7b-exl2-8bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DeepDream2045/NeuralDaredevil-7b-exl2-8bpw with Docker Model Runner:
```
docker model run hf.co/DeepDream2045/NeuralDaredevil-7b-exl2-8bpw
```

NeuralDaredevil-7B

NeuralDaredevil-7B is a DPO fine-tune of mlabonne/Daredevil-7B using the argilla/distilabel-intel-orca-dpo-pairs preference dataset and my DPO notebook from this article.

Thanks Argilla for providing the dataset and the training recipe here. 💪

🏆 Evaluation

Nous

The evaluation was performed using LLM AutoEval on Nous suite.

Model	Average	AGIEval	GPT4All	TruthfulQA	Bigbench
mlabonne/NeuralDaredevil-7B 📄	59.39	45.23	76.2	67.61	48.52
mlabonne/Beagle14-7B 📄	59.4	44.38	76.53	69.44	47.25
argilla/distilabeled-Marcoro14-7B-slerp 📄	58.93	45.38	76.48	65.68	48.18
mlabonne/NeuralMarcoro14-7B 📄	58.4	44.59	76.17	65.94	46.9
openchat/openchat-3.5-0106 📄	53.71	44.17	73.72	52.53	44.4
teknium/OpenHermes-2.5-Mistral-7B 📄	52.42	42.75	72.99	52.99	40.94

You can find the complete benchmark on YALL - Yet Another LLM Leaderboard.

Open LLM Leaderboard

Detailed results can be found here

Metric	Value
Avg.	74.12
AI2 Reasoning Challenge (25-Shot)	69.88
HellaSwag (10-Shot)	87.62
MMLU (5-Shot)	65.12
TruthfulQA (0-shot)	66.85
Winogrande (5-shot)	82.08
GSM8k (5-shot)	73.16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/NeuralDaredevil-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Prompt Tempalte

This model uses the same prompt template as mistralai/Mistral-7B-Instruct-v0.2

See instruction-format for more details

Downloads last month: 1

Model tree for DeepDream2045/NeuralDaredevil-7b-exl2-8bpw

Base model

mlabonne/Daredevil-7B

Quantized

(8)

this model

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

69.880
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

87.620
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

65.120
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

66.850
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

82.080
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

73.160