September 22th, 2023 - Revolutionary Speeds & Precision: The Future of Neural Networks and Language Models
Manage episode 377728266 series 3485608
Contenuto fornito da Marcus Edel. Tutti i contenuti dei podcast, inclusi episodi, grafica e descrizioni dei podcast, vengono caricati e forniti direttamente da Marcus Edel o dal partner della piattaforma podcast. Se ritieni che qualcuno stia utilizzando la tua opera protetta da copyright senza la tua autorizzazione, puoi seguire la procedura descritta qui https://it.player.fm/legal.
- Parallelizing non-linear sequential models over the sequence length
- Fast Feedforward Networks
- LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
- A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
- Boolformer: Symbolic Regression of Logic Functions with Transformers
Capitoli
1. Intro (00:00:00)
2. Parallelizing non-linear sequential models over the sequence length (00:01:33)
3. Fast Feedforward Networks (00:04:06)
4. LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models (00:06:53)
5. A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models (00:09:07)
6. Boolformer: Symbolic Regression of Logic Functions with Transformers (00:11:54)
75 episodi