Image-to-Text
Transformers
PyTorch
TensorBoard
Russian
English
vision-encoder-decoder
image-text-to-text
ocr
Inference Endpoints
File size: 205 Bytes
4787ac3
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
{
  "_from_model_config": true,
  "bos_token_id": 0,
  "decoder_start_token_id": 0,
  "eos_token_id": 2,
  "max_length": 64,
  "pad_token_id": 1,
  "transformers_version": "4.26.1",
  "use_cache": false
}