Model Card for Model ID

Training

Training loss performance:

Model	Belebele	MGSM Direct	Global MMLU	XCopa	XNLI	XStoryCloze
LLaMA3.2-1B-RandomInit	0.2667	0.0040	0.2504	0.4700	0.3361	0.4672
LLaMA3.2-1B-zh-pt-CulturaX-10B	0.2311	0.0160	0.2285	0.5200	0.3361	0.4851

Safetensors

Model size

1.24B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support