You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
It would be awesome to have a collection of standard inference methods, e.g. greedy, temperature, top-p, top-k, eventually tree / beam search and batched inference, once we support it on the backend.
For now, perhaps, it would be best to implement them as standalone functions / functors that take the full model as input and do the inference. Eventually, we'll figure out the best way of integrating them together.
Roadmap (tentative)
sampling, greedy, top-k, nucleus, etc -- with obligatory support for prefixes
inference with prompt-tuned model
beam search (requires changes on backend)
.. and then, in no particular order,
inference with LoRA / AdaMix
user-defined, constraints, other crazy stuff
The text was updated successfully, but these errors were encountered:
It would be awesome to have a collection of standard inference methods, e.g. greedy, temperature, top-p, top-k, eventually tree / beam search and batched inference, once we support it on the backend.
For now, perhaps, it would be best to implement them as standalone functions / functors that take the full model as input and do the inference. Eventually, we'll figure out the best way of integrating them together.
Roadmap (tentative)
.. and then, in no particular order,
The text was updated successfully, but these errors were encountered: