Clip-interrogator

* Support for more caption models. In addition to blip-base and blip-large there is now blip2-2.7b (15.5GB), blip2-flan-t5-xl (15.77GB), git-large-coco (1.58GB). See run_gradio.py for example.
* Newly exposed class LabelTable and functions list_caption_models, list_clip_models, load_list
* See README for example how to rank your own list of terms using LabelTable

* Improved low VRAM support. Use new `apply_low_vram_defaults` method on `Config` object
* Improved download of safetensors cache files
* Dropped support of the .pkl cache files in favor of safetensors format