sukii

Please run the output "This mvie did everthing a van dqmme mLvie shoHld do, which is martial arts and action" as input again to see if it progressively fixes it....

Looks more like QWERTY keyboard spelling mistake. Probably we need a QWERTY-distance based rather than Levenshtein distance based **spellcheck**

Yes, not only the speed improvement, but also that Linux pipes help in sending the output directly to the webservices avoiding possible collisions, racing conditions etc. Of course, the images...

https://gitlab.coko.foundation/XSweet/XSweet/-/tree/pdf2html/applications/pdf2html

``` >>> print(transformers.__version__) 4.40.0.dev0 ```

Please try pulling manually the model files directly from here to see if it works: ``` ... wget https://huggingface.co/jetmoe/jetmoe-8b-chat/resolve/main/tokenizer.model ... ```

Created a `github` repo for that: https://github.com/Sukii/jetmoe Managed to run `jetmoe-8b-chat` also (replace `AutoModelForCasualLM` by `JetMoEForCasualLM`). ``` The argument `trust_remote_code` is to be used with Auto classes. It has no...

Added pulling bash scripts in the model folders. Please move your discussions to the `github` repositary: https://github.com/Sukii/jetmoe

The => Dog => runs => down is 4 levels deep, while The => Nice => women is 3 levels deep. I suppose all trees must have the same depth...

Yes, but I suppose the end token is also a token with some probability, so in a sense the tree keeps going any way. These trees in reality have too...