Image-Text-to-Text
MLX
Safetensors
English
idefics2
multimodal
vision
File size: 92 Bytes
4499481
 
 
 
 
1
2
3
4
5
6
{
  "<end_of_utterance>": 32002,
  "<fake_token_around_image>": 32000,
  "<image>": 32001
}