Edan Weis
Edan Weis
Yes https://medium.com/@amanrusia/xlnet-speaks-comparison-to-gpt-2-ea1a4e9ba39e
In case anyone comes across this problem, my workaround: ```javascript if(!this.map.getLayer('my-layer-name')){ this.map.addLayer({ ...this.myLayer, id: 'my-layer-name', source: this.geojsonSource }) } ```
A [PyData 2019 presentation](https://pydata.org/delhi2019/schedule/presentation/22/knowledge-graph-made-simple-using-nlp-and-transfer-learning/) by Suyog S Swami has described one such approach.
@sinwoobang any updates? did you manage to re-sequence the messages for this custom model? I'm having trouble calling the OpenAICient from the custom model class.
> @edanweis I did. What part are you struggling with? Thanks @sinwoobang I managed with this ``` class PerplexityAIClient: def __init__(self, config: Dict[str, Any]): self._config = config self.model = config["model"]...
@sinwoobang Yes of course, nice catch! Thanks. I realised that perplexity online models are effectively search engines for which a message history doesn't make much sense. Perhaps this should be...
@Andrew2479 I have this error too. Did you solve it?
Fix "onToken" not called if no idToken found in cache
I'm having the same issue building a graph editor with Vue. Seems to be pointing to a worker file in the local development server > Failed to load module script:...
So I would have to build another custom component. It would be great to have a slot for a custom child component within the popup component