If one get an error message like this
ImportError: tokenizers>=0.21,<0.22 is required for a normal functioning of this module, but found tokenizers==0.20.3.
-after installing this node then do this
+one can fix this error message easily.
+ +## Error Fixing + +After installing of this node one has to do
```pip install -U transformers``` +and the error message is gone.
+ +## General Solution + +By changing the requirements.txt
+this error should no longer occur.
The one and only open issue is how to unload a loaded -model. Memory is locked after loading a model independend if the workflow -with the node is open or closed.
+Moondream model. Memory is locked after loading a model independend if the +workflow with the node is open or closed. # Do-Do -Improvement of the documentation. +Improvement of the documentation.
-The open issue that I did not found a way to unload a loaded model makes -much more test runs necessary. +The open issue that I did not found a way to unload +a loaded model makes much more test runs necessary.
-The algorithm I found works well for the moment. Some approaches I tried -before not. This has to be tested if this approach works all the time. - -Dependencies while installation have to be checked to prevent the error message -from the last section. In the past I solved this problem for my other programs. +The algorithm I found works well for the moment. +Some approaches I tried before not. This has to be tested if this approach +works all the time.
# References