In this work we introduce a new optimisation method called SAGA in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates.
In this paper, we show an avenue for aligning language models with user intent on a wide range of tasks by fine-tuning with human feedback.
By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.
Ranked #1 on Question Answering on CoQA (Overall metric)
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters.
Ranked #2 on Question Answering on PubChemQA
Multi-query attention (MQA), which only uses a single key-value head, drastically speeds up decoder inference.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
The small number of weights in a Sparse WaveRNN makes it possible to sample high-fidelity audio on a mobile CPU in real time.
In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function.
Ranked #1 on Speaker Verification on CALLHOME