Model Description

This is the meta-llama/Llama-3.2-1B base model fine tuned on the mlabonne/orpo-dpo-mix-40k dataset.

Evaluation Results

We used lm-evalutation-harness from EleutherAI to evaluate this fine-tuned version of meta-llama/Llama-3.2-1B on the 'Hellaswag' benchmark.

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
hellaswag	1	none	0	acc	↑	0.4773	±	0.0050
		none	0	acc_norm	↑	0.6358	±	0.0048

Safetensors

Model size

1.24B params

Tensor type

F32

Inference API

Unable to determine this model's library. Check the docs .

Base model

Finetuned

(94)

this model