Hugging Face's logo

basaadi
/
tifinagh-ocr

Image-Text-to-Text
Transformers
Safetensors
vision-encoder-decoder
Model card Files
xet
 Community
tifinagh-ocr
File size: 2,358 Bytes
86117a3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
{
  "architectures": [
    "VisionEncoderDecoderModel"
  ],
  "decoder": {
    "_name_or_path": "",
    "activation_dropout": 0.0,
    "activation_function": "gelu",
    "add_cross_attention": true,
    "architectures": null,
    "attention_dropout": 0.0,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "d_model": 384,
    "decoder_attention_heads": 6,
    "decoder_ffn_dim": 1536,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 3,
    "decoder_start_token_id": 2,
    "dropout": 0.1,
    "dtype": "float32",
    "eos_token_id": 2,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "init_std": 0.02,
    "is_decoder": true,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layernorm_embedding": true,
    "max_position_embeddings": 128,
    "model_type": "trocr",
    "output_attentions": false,
    "output_hidden_states": false,
    "pad_token_id": 1,
    "problem_type": null,
    "return_dict": true,
    "scale_embedding": false,
    "tie_word_embeddings": true,
    "use_cache": true,
    "use_learned_position_embeddings": true,
    "vocab_size": 81
  },
  "decoder_start_token_id": 1,
  "dtype": "float32",
  "encoder": {
    "_name_or_path": "",
    "architectures": null,
    "attention_probs_dropout_prob": 0.0,
    "chunk_size_feed_forward": 0,
    "dtype": "float32",
    "encoder_stride": 16,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 384,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": [
      64,
      256
    ],
    "initializer_range": 0.02,
    "intermediate_size": 1536,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-12,
    "model_type": "vit",
    "num_attention_heads": 6,
    "num_channels": 3,
    "num_hidden_layers": 6,
    "output_attentions": false,
    "output_hidden_states": false,
    "patch_size": 16,
    "pooler_act": "tanh",
    "pooler_output_size": 384,
    "problem_type": null,
    "qkv_bias": true,
    "return_dict": true
  },
  "eos_token_id": 2,
  "is_encoder_decoder": true,
  "model_type": "vision-encoder-decoder",
  "pad_token_id": 0,
  "tie_word_embeddings": false,
  "transformers_version": "5.5.4",
  "vocab_size": 81
}