Malaysian CausalLM - a mesolitica Collection

mesolitica 's Collections

Malaysian Mistral

Malaysian Llama

Malaysian Gemma

Malaysian Embedding

Malaysian Reranker

Malaysian CausalLM

Malaysian LLM2Vec

Malaysian Seq2Seq

Malaysian MaskLM

Malaysian pretraining dataset

Malay instructions dataset

Malaysian synthetic dataset

Speech-to-Text dataset

Malaysian Whisper

Text-to-Speech dataset

Malaysian Text-to-Speech

Malaysian Noisy Translation

Google Translate dataset

Visual Multimodal dataset

Audio Multimodal dataset

Multimodal Malaysian LLM

Malaysian CausalLM

updated Dec 23, 2024

Trained on 21B tokens, 91GB of cleaned texts, able to understand standard Malay, local Malay, local Mandarin, Manglish, and local Tamil.