NOT-HAL9000

Onyx + TensorRT support for XLM-R Large Vit-B/16+?

3

Just wondering if this is possible? Thanks!

Does the text generation instructions work for the ByT5 models? (byte-by-byte T5)?

1

As the question states, does transformer-deploy text generation work on the byt5 models? (google/byt5-small, google/byt5-base etc..)? Basically ByT5 works on raw UTF-8 bytes and can be used without a tokenizer....

sam-as-a-service | Segment anything as a service possible?

2

Would it be possible to consider creating a segment anything as a service, using the new [sam model](https://segment-anything.com/)? Thanks

Compatibility with OWL-ViT

1

Would it be possible to get this working with OWL-ViT? https://segments.ai/blog/zero-shot-object-detection-with-owl-vit

Feature: Support NATS.io stream ingestion

5

I am using Memgraph Lab and the available options to add a new stream are 'Kafka/Redpanda' and 'Pulsar'. Would it be possible to add support for ingestion streams from [nats.io](https://docs.nats.io/nats-concepts/jetstream/streams)?...

Enhancement: Detailed analytics/admin dashboard for Self-Hosted Livekit

6

I'm creating this issue to track any movement towards providing a detailed analytics / admin dashboard for self-hosted Livekit. It could be in many flavours: - Provide a localhost dashboard...

This would be pretty cool to integrate. Especially for quick component designs

https://arxiv.org/abs/2211.06482

Could you please upload the trained model for the tennis example (and possibly other examples) with the data so we don't have to retrain the models just to test it...