AlfRjw/NeuralDaredevil-8B-abliterated-Q2-mlx
The Model AlfRjw/NeuralDaredevil-8B-abliterated-Q2-mlx was converted to MLX format from mlabonne/NeuralDaredevil-8B-abliterated using mlx-lm version 0.20.5.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("AlfRjw/NeuralDaredevil-8B-abliterated-Q2-mlx")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
- Downloads last month
- 1
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for AlfRjw/NeuralDaredevil-8B-abliterated-Q2-mlx
Base model
mlabonne/NeuralDaredevil-8B-abliteratedDataset used to train AlfRjw/NeuralDaredevil-8B-abliterated-Q2-mlx
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