Skip to content
Change the repository type filter

All

    Repositories list

    • We gather Malaysian dataset! https://malaysian-dataset.readthedocs.io/
      Jupyter Notebook
      Apache License 2.0
      10830463Updated Nov 26, 2024Nov 26, 2024
    • 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      Apache License 2.0
      27k200Updated Nov 25, 2024Nov 25, 2024
    • malaya

      Public
      Natural Language Toolkit for Malaysian language, https://malaya.readthedocs.io/
      Jupyter Notebook
      MIT License
      12747039Updated Nov 25, 2024Nov 25, 2024
    • Dynamic batching for Document Layout and OCR, suitable for RAG, with extra tools.
      Jupyter Notebook
      1900Updated Nov 25, 2024Nov 25, 2024
    • Dynamic batching for Speech Enhancement and diffusion based TTS
      Jupyter Notebook
      0300Updated Nov 25, 2024Nov 25, 2024
    • Lightweight continuous batching OpenAI compatibility using HuggingFace Transformers include T5 and Whisper.
      Python
      21520Updated Nov 24, 2024Nov 24, 2024
    • 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      Apache License 2.0
      27k000Updated Nov 22, 2024Nov 22, 2024
    • cookbook

      Public
      cookbooks 📖 for Mesolitica products!
      Jupyter Notebook
      MIT License
      1600Updated Nov 18, 2024Nov 18, 2024
    • Brand new TTS solution
      Python
      Other
      1.1k000Updated Nov 18, 2024Nov 18, 2024
    • Speech Toolkit for Malaysian language, https://malaya-speech.readthedocs.io/
      Jupyter Notebook
      MIT License
      4224060Updated Nov 12, 2024Nov 12, 2024
    • Vue
      1400Updated Oct 25, 2024Oct 25, 2024
    • Context Parallelism, support Blockwise Attention, Ring Attention and Tree Attention.
      Jupyter Notebook
      3220Updated Oct 24, 2024Oct 24, 2024
    • Python
      Apache License 2.0
      4.7k100Updated Oct 5, 2024Oct 5, 2024
    • Preprint under Mesolitica.
      TeX
      1100Updated Sep 2, 2024Sep 2, 2024
    • Customizable Web Chat Widget 💬
      JavaScript
      0000Updated Aug 25, 2024Aug 25, 2024
    • A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      Apache License 2.0
      4.7k200Updated Aug 17, 2024Aug 17, 2024
    • Learning more memory efficient on top of Llama model!
      Jupyter Notebook
      2200Updated Aug 2, 2024Aug 2, 2024
    • A high-throughput and memory-efficient inference and serving engine for Whisper, https://mesolitica.com/blog/vllm-whisper
      Python
      Apache License 2.0
      4.7k1800Updated Jul 28, 2024Jul 28, 2024
    • t5-sdpa

      Public
      🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      Apache License 2.0
      27k000Updated Jul 5, 2024Jul 5, 2024
    • 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      Apache License 2.0
      27k100Updated Jun 9, 2024Jun 9, 2024
    • 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      Apache License 2.0
      27k000Updated May 31, 2024May 31, 2024
    • 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      Apache License 2.0
      27k400Updated May 14, 2024May 14, 2024
    • Finetune Malaysian LLM for Malaysian context embedding task.
      Jupyter Notebook
      12001Updated Apr 27, 2024Apr 27, 2024
    • Super simple website application streaming Playwright agent using websocket that support multi-users including queue, 100% no LangChain, 100% no LlamaIndex, 100% use available models from HuggingFace.
      Python
      2500Updated Apr 2, 2024Apr 2, 2024
    • Benchmarking LLM for Malay tasks.
      Jupyter Notebook
      5400Updated Apr 1, 2024Apr 1, 2024
    • Tensorflow freeze graph optimization and boilerplates to share among Malaya projects.
      Python
      MIT License
      1100Updated Mar 26, 2024Mar 26, 2024
    • Multi-Modal Language Modeling with Image, Audio and Text Integration, included multi-images and multi-audio in a single multiturn.
      Jupyter Notebook
      11400Updated Feb 20, 2024Feb 20, 2024
    • Benchmarking Embedding models for Malaysian context.
      Jupyter Notebook
      1100Updated Feb 15, 2024Feb 15, 2024
    • Benchmarking Malaysian Speech-to-Text models.
      Jupyter Notebook
      1600Updated Feb 6, 2024Feb 6, 2024
    • jgscm

      Public
      Jupyter support for Google Cloud Storage
      Python
      MIT License
      20000Updated Jul 7, 2021Jul 7, 2021