Daan Grashoff

It's because it tries first the public api which doesn't provide this info. Only the private api will

It seems that you run it with --mode feature, instead of --mode score

> My team has been hacking on this from the parent component, using `window.PDFViewer`; beyond being kind of gross in using a global intended for debug, I believe it's the...

Awesome! Thanks, I'm gonna check it out!

@chintanckg Which image are you using? 763104351884.dkr.ecr.us-east-2.amazonaws.com/huggingface-pytorch-tgi-inference:2.0.1-tgi1.1.0-gpu-py39-cu118-ubuntu20.04 or 763104351884.dkr.ecr.us-east-2.amazonaws.com/huggingface-pytorch-tgi-inference:2.0.1-tgi1.1.0-gpu-py39-cu118-ubuntu20.04-v1.0

Can you share your code?

Hey @eyurtsev, Not a problem! I depend on on_chain_start, and without modifying it, the input remains consistently empty. I also observed that when using something like StrOutputParser, only the initial...

Yep totally get it! I'll use my forked version in the meantime, and will wait on the full fix for this :) Also totally missed that! updating the input on...

They have multiple versions, but none are working with AWQ models: ```{ "imageDetails": [ { "registryId": "763104351884", "repositoryName": "huggingface-pytorch-tgi-inference", "imageDigest": "sha256:2739b630b95d8a95e6b4665e66d8243dd43b99c4fdb865feff13aab9c1da06eb", "imageTags": [ "2.0.1-gpu-py39-cu118-ubuntu20.04", "2.0-tgi1.1-gpu-py39-cu118-ubuntu20.04", "2.0-gpu-py39-cu118-ubuntu20.04-v1", "2.0.1-tgi1.1.0-gpu-py39-cu118-ubuntu20.04-v1.0-2023-10-02-14-29-28", "2.0-tgi1.1-gpu-py39-cu118-ubuntu20.04-v1", "2.0.1-tgi1.1.0-gpu-py39-cu118-ubuntu20.04", "2.0.1-tgi1.1.0-gpu-py39-cu118-ubuntu20.04-v1.0"...