Logan Lebanoff

Release output summaries?

1

Can you release the output summaries on the test sets? I'm mostly interested in the summaries for CNN/DailyMail and XSum. It would be really helpful for me and likely many...

Larger models like GPT-J and GPT-NeoX-20B

3

Has this library been tested with larger models such as GPT-J-6B and GPT-NeoX-20B? Are there plans to support larger models like these? Thanks.

Grammar not working

1

Running the sample wav file with a grammar gives no change in the output compared to without the grammar. I'm purposefully not giving any prompt because I want to see...

Zero config not working for VLMs

1

### System Info OS: Ubuntu 20.04 Docker setup: docker-compose.yml ``` services: tgi: image: ghcr.io/huggingface/text-generation-inference:3.2.3 command: --model-id ${MODEL} environment: - HF_TOKEN=${HUGGING_FACE_HUB_TOKEN} ports: - "80:80" volumes: - ~/.cache/huggingface/hub:/data deploy: resources: reservations: devices:...