Douglas Hanley f54932ce66 llama : support batched embeddings (#5466) ...

* batched embedding: pool outputs by sequence id. updated embedding example

* bring back non-causal attention

* embd : minor improvements

* llama : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

2024-02-13 14:06:58 +02:00

40 KiB

Raw Blame History

View Raw