Commits on Sep 22, 2024

1. Support multiple tokenizers and other layers with assets …

   Preset saving and loading does not currently generalize to multiple
   tokenizers (or other preprocessor with static assets), this is a work
   in progress PR towards adding it, specifically for stable diffusion.
   
   The high-level api would allow something like this
   
   ```python
   # High-level loading.
   image_to_text = keras_hub.models.ImageToText.from_preset(
       "sd3_preset",
   )
   # Low-level tokenizer loading.
   clip_l_tokenizer = kersa_hub.tokenizers.Tokenizer.from_preset(
       "sd3_preset", config_file="clip_l_tokenizer.json",
   )
   clip_g_tokenizer = kersa_hub.tokenizers.Tokenizer.from_preset(
       "sd3_preset", config_file="clip_g_tokenizer.json",
   )
   ```
   
   During conversion, we would need to make sure each tokenizer was
   created with a separate `config_file` passed to the constructor. Then
   when calling `task.save_to_preset("path")`, you would get the following
   structure.
   
   ```
   assets/clip_l_tokenizer/...
   assets/clip_g_tokenizer/...
   assets/t5_tokenizer/...
   clip_l_tokenizer.json
   clip_g_tokenizer.json
   t5_tokenizer.json
   ```

   

   mattdangerw committed Sep 22, 2024
   Configuration menu

   • View commit details
   • Copy full SHA for 5bdfdea
   • Browse repository at this point

   Copy the full SHA

   5bdfdea View commit details

   Browse the repository at this point in the history