mysterybox
Re:Scaling Transformer to 1M tokens and beyond with RMT
on Monday April 24, 2023 @04:02AM (#35684857)
Re:Scaling Transformer to 1M tokens and beyond with RMT
on Monday April 24, 2023 @04:02AM (#35684855)
Re:Scaling Transformer to 1M tokens and beyond with RMT
on Monday April 24, 2023 @04:01AM (#35684848)
github repo with code: https://github.com/booydar/t5-experiments/tree/scaling-repor...
Re:Code for Scaling Transformer to 1M tokens and beyond with RMT (arxi...
on Monday April 24, 2023 @03:26AM (#35684626)
Re:Code for Scaling Transformer to 1M tokens and beyond with RMT (arxi...
on Monday April 24, 2023 @03:26AM (#35684621)
Code for Scaling Transformer to 1M tokens and beyond with RMT (arxiv.org)
Re:Code for Scaling Transformer to 1M tokens and beyond with RMT (arxi...
on Monday April 24, 2023 @03:23AM (#35684602)
I found this interesting link in paper, so this can be used as ready code for RMT Transformer
https://github.com/booydar/t5-experiments/tree/scaling-repor...
ML Codecs Similar to Encodec by Facebook?
Re:Whisper Jax: Transcribe a 1 hour of audio in under 15 seconds
on Saturday April 22, 2023 @01:54AM (#35663773)
Whisper JAX is an optimised implementation of the Whisper model by OpenAI. It runs on JAX with a TPU v4-8 in the backend. Compared to PyTorch on an A100 GPU, it is over 70x faster, making it the fastest Whisper API available.
Whisper Jax: Transcribe a 1 hour of audio in under 15 seconds
Re:Bark – GPT-style realistic multilingual text-to-speech generation
on Thursday April 20, 2023 @02:12PM (#35643910)
WTH1!!!
Re:Ask HN: Modern alternatives to text-ada-embedding?
on Monday April 17, 2023 @06:26AM (#35598884)
thanks
Ask HN: Modern alternatives to text-ada-embedding?
Hello everyone,I'm currently searching for alternatives to text-ada-embedding, as I'm looking for a way to perform similarity search and embed PDF documents without having to pay OpenAI's fees.