Malaysian MaskLM - a mesolitica Collection

mesolitica 's Collections

Research papers

Malaysian Mistral

Malaysian Llama

Malaysian Gemma

Malaysian Embedding

Malaysian Reranker

Malaysian CausalLM

Malaysian LLM2Vec

Malaysian Seq2Seq

Malaysian MaskLM

Malaysian Text-to-Speech

Speech-to-Text dataset

Malaysian pretraining dataset

Malay instructions dataset

Malaysian synthetic dataset

Text-to-Speech dataset

Malaysian Noisy Translation

Malaysian Whisper

Google Translate dataset

Multimodal Malaysian dataset

Multimodal Malaysian LLM

Malaysian Real-time Conformer CTC

Social media snapshot

Malaysian MaskLM

updated Sep 22

Trained on 17B tokens, 81GB of cleaned texts, able to understand standard Malay, local Malay, local Mandarin, Manglish, and local Tamil.