koshyviv
koshyviv
Would love to see this feature
True, had to manually stop the command and rerun to see new logs.
This is a good alternative, thanks!
I'm having the same issue, only the download bit doesn't work. Tried clearing all data too. I'm on MIUI, if it helps
I was able to resolve by adding ``` if hasattr(passages, 'passages'): passages = passages.passages ``` after this line https://github.com/stanfordnlp/dspy/blob/42a5943379d28d1673dc8fe332a3d596efdfc7a3/dsp/primitives/search.py#L12 It seems that we are getting a prediction object as the...
We're seeing that issue, even with RMs - Issue https://github.com/stanfordnlp/dspy/issues/166 If it helps - the current workaround i am using is https://github.com/stanfordnlp/dspy/pull/486 - but I'm not sure if its the...
Doesnt answer your question directly - but you can try serving the quantized model via TGI (text-generation-inference) and use that endpoint in `HFClientTGI`
Shooting in the open here: 1. Does in work when you hit it via cURL? 2. Can you try with stream disabled?
The Readme is correct, instead of running `docker-compose up` in `default_configs` - you need to run it within the example you want after editing the `docker-compose.yml` Eg: ``` cd tmp/label-studio-ml-backend/label_studio_ml/examples/segment_anything_model...
Im facing something similar, were you able to find out what was going wrong?