license: llama3 tags:

• dpo datasets:
• mlabonne/orpo-dpo-mix-40k model-index:
• name: Daredevil-8B-abliterated-dpomix results:
  • task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics:
    • type: acc_norm value: 69.28 name: normalized accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B-abliterated-dpomix name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics:
    • type: acc_norm value: 85.05 name: normalized accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B-abliterated-dpomix name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics:
    • type: acc value: 69.1 name: accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B-abliterated-dpomix name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics:
    • type: mc2 value: 60 source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B-abliterated-dpomix name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics:
    • type: acc value: 78.69 name: accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B-abliterated-dpomix name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics:
    • type: acc value: 71.8 name: accuracy source: url: >- https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Daredevil-8B-abliterated-dpomix name: Open LLM Leaderboard base_model:
• mlabonne/Daredevil-8B-abliterated

NeuralDaredevil-8B-abliterated

image/jpeg

This is a DPO fine-tune of mlabonne/Daredevil-8-abliterated, trained on one epoch of mlabonne/orpo-dpo-mix-40k. The DPO fine-tuning successfully recovers the performance loss due to the abliteration process, making it an excellent uncensored model.

🔎 Applications

NeuralDaredevil-8B-abliterated performs better than the Instruct model on my tests.

You can use it for any application that doesn't require alignment, like role-playing. Tested on LM Studio using the "Llama 3" and "Llama 3 v2" presets.

⚡ Quantization

Thanks to QuantFactory, ZeroWw, Zoyd, solidrust, and tarruda for providing these quants.

• GGUF: https://huggingface.co/QuantFactory/NeuralDaredevil-8B-abliterated-GGUF
• GGUF (FP16): https://huggingface.co/ZeroWw/NeuralDaredevil-8B-abliterated-GGUF
• EXL2: https://huggingface.co/Zoyd/mlabonne_NeuralDaredevil-8B-abliterated-4_0bpw_exl2
• AWQ: https://huggingface.co/solidrust/NeuralDaredevil-8B-abliterated-AWQ
• ollama:
  • 16-bit: https://ollama.com/tarruda/neuraldaredevil-8b-abliterated
  • 8-bit: https://ollama.com/lstep/neuraldaredevil-8b-abliterated
  • 5-bit: https://ollama.com/closex/neuraldaredevil-8b-abliterated

🏆 Evaluation

Open LLM Leaderboard

NeuralDaredevil-8B is the best-performing uncensored 8B model on the Open LLM Leaderboard (MMLU score).

image/png

Nous

Evaluation performed using LLM AutoEval. See the entire leaderboard here.

🌳 Model family tree

image/png

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/Daredevil-8B"
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"])