Can't generate dectent text out of it
Am I missing something or this upload has some issues? it's not generating any text trhat makes sense.
You have to use the implementation from https://github.com/mustafaaljadery/gemma-2B-10M
You have to use the implementation from https://github.com/mustafaaljadery/gemma-2B-10M
Out of curiosity, have you been able to run the current repo implementation under ./src ?
If so, did you had you modified it?
Currently on consumer hardware few ppl including me are getting TypeError: GemmaModel.forward() got an unexpected keyword argument 'cache_position'
You have to use the implementation from https://github.com/mustafaaljadery/gemma-2B-10M
Out of curiosity, have you been able to run the current repo implementation under ./src ?
If so, did you had you modified it?
Currently on consumer hardware few ppl including me are gettingTypeError: GemmaModel.forward() got an unexpected keyword argument 'cache_position'
Same here, using the model from the repo gives cache_position error
any chance of seeing cache_position error getting fixed?
TypeError: GemmaModel.forward() got an unexpected keyword argument 'cache_position'. run th code ,the same error? Do anyone have the same problem?