Model Card

Model Description

This is a Large Language Model (LLM) trained on a subset of the dataset "mlabonne/orpo-dpo-mix-40k".

Evaluation Results

Hellaswag

Metric Value
Accuracy 0.4517

How to Use

To use this model, simply download the checkpoint and load it into your preferred deep learning framework.

Downloads last month
9
Safetensors
Model size
1B params
Tensor type
F32
·
Inference Providers NEW

Model tree for d4niel92/llama-3.2-1B-orpo

Finetuned
(883)
this model

Dataset used to train d4niel92/llama-3.2-1B-orpo