Quantization made by Richard Erkhov.

NeuralDaredevil-8B-abliterated - GGUF

Model creator: https://huggingface.co/mlabonne/
Original model: https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated/

Name	Quant method	Size
NeuralDaredevil-8B-abliterated.Q2_K.gguf	Q2_K	2.96GB
NeuralDaredevil-8B-abliterated.IQ3_XS.gguf	IQ3_XS	3.28GB
NeuralDaredevil-8B-abliterated.IQ3_S.gguf	IQ3_S	3.43GB
NeuralDaredevil-8B-abliterated.Q3_K_S.gguf	Q3_K_S	3.41GB
NeuralDaredevil-8B-abliterated.IQ3_M.gguf	IQ3_M	3.52GB
NeuralDaredevil-8B-abliterated.Q3_K.gguf	Q3_K	3.74GB
NeuralDaredevil-8B-abliterated.Q3_K_M.gguf	Q3_K_M	3.74GB
NeuralDaredevil-8B-abliterated.Q3_K_L.gguf	Q3_K_L	4.03GB
NeuralDaredevil-8B-abliterated.IQ4_XS.gguf	IQ4_XS	4.18GB
NeuralDaredevil-8B-abliterated.Q4_0.gguf	Q4_0	4.34GB
NeuralDaredevil-8B-abliterated.IQ4_NL.gguf	IQ4_NL	4.38GB
NeuralDaredevil-8B-abliterated.Q4_K_S.gguf	Q4_K_S	4.37GB
NeuralDaredevil-8B-abliterated.Q4_K.gguf	Q4_K	4.58GB
NeuralDaredevil-8B-abliterated.Q4_K_M.gguf	Q4_K_M	4.58GB
NeuralDaredevil-8B-abliterated.Q4_1.gguf	Q4_1	4.78GB
NeuralDaredevil-8B-abliterated.Q5_0.gguf	Q5_0	5.21GB
NeuralDaredevil-8B-abliterated.Q5_K_S.gguf	Q5_K_S	5.21GB
NeuralDaredevil-8B-abliterated.Q5_K.gguf	Q5_K	5.34GB
NeuralDaredevil-8B-abliterated.Q5_K_M.gguf	Q5_K_M	5.34GB
NeuralDaredevil-8B-abliterated.Q5_1.gguf	Q5_1	5.65GB
NeuralDaredevil-8B-abliterated.Q6_K.gguf	Q6_K	6.14GB
NeuralDaredevil-8B-abliterated.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: other 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: 60.0 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

NeuralDaredevil-8B-abliterated

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" preset.

⚡ Quantization

Thanks to QuantFactory, Zoyd, and solidrust for providint these quants.

🏆 Evaluation

Open LLM Leaderboard

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

Nous

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

Model	Average	AGIEval	GPT4All	TruthfulQA	Bigbench
mlabonne/NeuralDaredevil-8B-abliterated 📄	55.87	43.73	73.6	59.36	46.8
mlabonne/Daredevil-8B 📄	55.87	44.13	73.52	59.05	46.77
mlabonne/Daredevil-8B-abliterated 📄	55.06	43.29	73.33	57.47	46.17
NousResearch/Hermes-2-Theta-Llama-3-8B 📄	54.28	43.9	72.62	56.36	44.23
openchat/openchat-3.6-8b-20240522 📄	53.49	44.03	73.67	49.78	46.48
meta-llama/Meta-Llama-3-8B-Instruct 📄	51.34	41.22	69.86	51.65	42.64
meta-llama/Meta-Llama-3-8B 📄	45.42	31.1	69.95	43.91	36.7

🌳 Model family tree

💻 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"])