| { | |
| "additional_special_tokens": [ | |
| "<|im_start|>", | |
| "<|im_end|>", | |
| "<|object_ref_start|>", | |
| "<|object_ref_end|>", | |
| "<|box_start|>", | |
| "<|box_end|>", | |
| "<|quad_start|>", | |
| "<|quad_end|>", | |
| "<|vision_start|>", | |
| "<|vision_end|>", | |
| "<|vision_pad|>", | |
| "<|image_pad|>", | |
| "<|video_pad|>", | |
| "<img>", | |
| "</img>", | |
| "<IMG_CONTEXT>", | |
| "<quad>", | |
| "</quad>", | |
| "<ref>", | |
| "</ref>", | |
| "<box>", | |
| "</box>" | |
| ], | |
| "context_image_token": "<IMG_CONTEXT>", | |
| "end_image_token": "</img>", | |
| "eos_token": { | |
| "content": "<|im_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "start_image_token": "<img>", | |
| "video_token": "<video>" | |
| } | |