Tag: quantization
- SeamlessM4T-Massively Multilingual & Multimodal Machine Translation (05 Sep 2023)
This is my reading note 2/2 on SeamlessM4T-Massively Multilingual & Multimodal Machine Translation. It is end to end multi language translation system supports multimodality (text and audio). This paper also provides a good review on machine translation. This note focus on data preparation part of the paper and please read SeamlessM4T-data for the other part.
- SeamlessM4T-Massively Multilingual & Multimodal Machine Translation (04 Sep 2023)
This is my reading note 1/2 on SeamlessM4T-Massively Multilingual & Multimodal Machine Translation. It is end to end multi language translation system supports multimodality (text and audio). This paper also provides a good review on machine translation. This note focus on data preparation part of the paper and please read SeamlessM4T-model for the other part.
- Billion-scale similarity search with GPUs (11 Aug 2023)
This is my reading note on Billion-scale similarity search with GPUs. FAISS (Facebook AI Similarity Search) is an open-source library that allows developers to quickly search for similar embeddings of multimedia documents. FAISS uses indexing structures like LSH, IVF, and PQ to speed up the search. It also supports GPUs, which can further accelerate the search. FAISS was developed by Facebook AI Research (FAIR).
- Network Compression (03 Apr 2019)
The trained network is typically too large to run efficiently on mobile device. For example, VGG16 used for image classification has more 130 Million parameter (about 600 MB on model size) and requires about 31 billion operations to classify an image, which is way to expensive to be done on mobile.