OpenLLaMA 3B Thai

We are extending Thai vocabulary to OpenLLaMA 3B v2 and do continue pretraining with English and Thai datasets.

Dataset

[WIP]

Acknowledgements

Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC). We use TPUv4-64 for training model about 4 days / 1 epoch.

Thank you TPU Research Cloud and EasyLM project! We use EasyLM for pretraining model.

Downloads last month: 88

Safetensors

Model size

3.46B params

Tensor type

FP16

Inference API

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.