metadata
base_model: HuggingFaceTB/SmolLM-360M
language:
- ms
- en
HuggingFaceTB/SmolLM-360M continue pretraining on Malaysian context dataset
Continue pretraining on 50B tokens, dataset prepared at https://github.com/malaysia-ai/pretrain-text-dataset/tree/main/smollm
Wandb at https://wandb.ai/huseinzol05/finetune-HuggingFaceTB-SmolLM-360M/