Ceyda Cinarel (재이다)

would it be possible to get driver_version and cuda_version (if available) in the json output?

the ansi conversion was making the text hard to parse in the websocket response

Because otherwise websocket returns info formatted with html (with tags, and some stats left out), due to conversion done here: `return ansi_conv.convert(body, full=False)` the response looks like this: ```html [0]...

I was looking at the example in the article and the one thing that jumped out at me as a potential source of confusion (especially for newcomers) was `weights.transforms()`. Although...

This is also an interesting method/library for evaluating text generation https://github.com/neulab/BARTScore

I guess this isn't referring to the huggingface datasets but the detr repo's https://github.com/facebookresearch/detr/tree/main/datasets

Looks like those flags don't mean no half precision, but rather means use torch half ops instead of cuda's. ref:https://discuss.pytorch.org/t/cuda-no-half2-operators-for-cuda-9-2/18365/4 Anyway, I think I managed to get it to work...not...

Any progress on this?

you want torchserve to start as soon as you run the torchserve-dashboard command? If so, you can add a call to `ts.start_torchserve()` on line 140 of dash.py. (first clone the...

> I can add the API I already wrote and we can work from there. > I'll have to check for write permissions. ah didn't think of that 🤦 I...