mlx-community/NeuralDaredevil-8B-abliterated-4bit
The Model mlx-community/NeuralDaredevil-8B-abliterated-4bit was converted to MLX format from mlabonne/NeuralDaredevil-8B-abliterated using mlx-lm version 0.16.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/NeuralDaredevil-8B-abliterated-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 78
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Dataset used to train mlx-community/NeuralDaredevil-8B-abliterated-4bit
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard69.280
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.050
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard69.100
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard60.000
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.690
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard71.800