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