python -m utils.extend_model_vocab --original_model_ckpt /folder/to/old/model --extended_model_ckpt /folder/to/extended/model Once the extension has worked, one can fine-tune using the newly created model checkpoint in /folder/to/extended/model....
.├── text_encoder │ └── model.safetensors ├── text_encoder_2 │ ├── model-00001-of-00002.safetensors │ └── model-00002-of-00002.safetensors ├── tokenizer │ ├── merges.txt │ ├── special_tokens_map.json │ ├── tokenizer_config.json │ └── vocab....