• Pablo Montalvo's avatar
    Paligemma causal attention mask (#30967) · a25f7d3c
    Pablo Montalvo authored
    
    
    * PaliGemma working causal attention
    
    * Formatting
    
    * Style
    
    * Docstrings + remove commented code
    
    * Update docstring for PaliGemma Config
    
    * PaliGemma - add separator ind to model/labels
    
    * Refactor + docstring paligemma processor method
    
    * Style
    
    * return token type ids when tokenizing labels
    
    * use token type ids when building causal mask
    
    * add token type ids to tester
    
    * remove separator from config
    
    * fix style
    
    * don't ignore separator
    
    * add processor documentation
    
    * simplify tokenization
    
    * fix causal mask
    
    * style
    
    * fix label propagation, revert suffix naming
    
    * fix style
    
    * fix labels tokenization
    
    * [run-slow]paligemma
    
    * add eos if suffixes are present
    
    * [run-slow]paligemma
    
    * [run-slow]paligemma
    
    * add misssing tokens to fast version
    
    * Apply suggestions from code review
    Co-authored-by: default avatarArthur <48595927+ArthurZucker@users.noreply.github.com>
    
    * fix style
    
    * [run-slow]paligemma
    
    ---------
    Co-authored-by: default avatarPeter Robicheaux <peter@roboflow.com>
    Co-authored-by: default avatarArthur <48595927+ArthurZucker@users.noreply.github.com>
    a25f7d3c
test_modeling_paligemma.py 16.8 KB