Hugging Face's logo

Tamazight
/
TrOCR-Tifinagh-Small

Image-Text-to-Text
Transformers
Safetensors
Standard Moroccan Tamazight
Central Atlas Tamazight
Tachelhit
vision-encoder-decoder
Model card Files
xet
 Community
Akseltinfat commited on
Commit
6b7196e
·
verified ·
1 Parent(s): 0c84fcb

Upload model

Browse files
Files changed (3) hide show
  1. config.json +122 -0
  2. generation_config.json +39 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "bos_token_id": 2,
6
+ "decoder": {
7
+ "_name_or_path": "",
8
+ "activation_dropout": 0.0,
9
+ "activation_function": "relu",
10
+ "add_cross_attention": true,
11
+ "architectures": null,
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 0,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": 0.0,
16
+ "cross_attention_hidden_size": 384,
17
+ "d_model": 256,
18
+ "decoder_attention_heads": 8,
19
+ "decoder_ffn_dim": 1024,
20
+ "decoder_layerdrop": 0.0,
21
+ "decoder_layers": 6,
22
+ "decoder_start_token_id": 2,
23
+ "dropout": 0.1,
24
+ "dtype": "float32",
25
+ "eos_token_id": 2,
26
+ "finetuning_task": null,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "init_std": 0.02,
32
+ "is_decoder": true,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "layernorm_embedding": true,
39
+ "max_position_embeddings": 512,
40
+ "model_type": "trocr",
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "pad_token_id": 1,
44
+ "prefix": null,
45
+ "problem_type": null,
46
+ "pruned_heads": {},
47
+ "return_dict": true,
48
+ "scale_embedding": true,
49
+ "sep_token_id": null,
50
+ "task_specific_params": null,
51
+ "tie_encoder_decoder": false,
52
+ "tie_word_embeddings": false,
53
+ "tokenizer_class": null,
54
+ "torchscript": false,
55
+ "use_bfloat16": false,
56
+ "use_cache": false,
57
+ "use_learned_position_embeddings": true,
58
+ "vocab_size": 82
59
+ },
60
+ "decoder_start_token_id": 2,
61
+ "dtype": "float32",
62
+ "encoder": {
63
+ "_name_or_path": "",
64
+ "add_cross_attention": false,
65
+ "architectures": null,
66
+ "attention_probs_dropout_prob": 0.0,
67
+ "bos_token_id": null,
68
+ "chunk_size_feed_forward": 0,
69
+ "cross_attention_hidden_size": null,
70
+ "decoder_start_token_id": null,
71
+ "dtype": "float32",
72
+ "encoder_stride": 16,
73
+ "eos_token_id": null,
74
+ "finetuning_task": null,
75
+ "hidden_act": "gelu",
76
+ "hidden_dropout_prob": 0.0,
77
+ "hidden_size": 384,
78
+ "id2label": {
79
+ "0": "LABEL_0",
80
+ "1": "LABEL_1"
81
+ },
82
+ "image_size": 384,
83
+ "initializer_range": 0.02,
84
+ "intermediate_size": 1536,
85
+ "is_decoder": false,
86
+ "is_encoder_decoder": false,
87
+ "label2id": {
88
+ "LABEL_0": 0,
89
+ "LABEL_1": 1
90
+ },
91
+ "layer_norm_eps": 1e-12,
92
+ "model_type": "deit",
93
+ "num_attention_heads": 6,
94
+ "num_channels": 3,
95
+ "num_hidden_layers": 12,
96
+ "output_attentions": false,
97
+ "output_hidden_states": false,
98
+ "pad_token_id": null,
99
+ "patch_size": 16,
100
+ "pooler_act": "tanh",
101
+ "pooler_output_size": 384,
102
+ "prefix": null,
103
+ "problem_type": null,
104
+ "pruned_heads": {},
105
+ "qkv_bias": true,
106
+ "return_dict": true,
107
+ "sep_token_id": null,
108
+ "task_specific_params": null,
109
+ "tie_encoder_decoder": false,
110
+ "tie_word_embeddings": true,
111
+ "tokenizer_class": null,
112
+ "torchscript": false,
113
+ "use_bfloat16": false
114
+ },
115
+ "eos_token_id": 3,
116
+ "is_encoder_decoder": true,
117
+ "model_type": "vision-encoder-decoder",
118
+ "pad_token_id": 0,
119
+ "tie_word_embeddings": false,
120
+ "transformers_version": "5.0.0",
121
+ "vocab_size": 82
122
+ }
generation_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": false,
3
+ "assistant_confidence_threshold": 0.4,
4
+ "assistant_lookbehind": 10,
5
+ "bos_token_id": 2,
6
+ "decoder_start_token_id": 2,
7
+ "diversity_penalty": 0.0,
8
+ "do_sample": false,
9
+ "early_stopping": true,
10
+ "encoder_no_repeat_ngram_size": 0,
11
+ "encoder_repetition_penalty": 1.0,
12
+ "eos_token_id": [
13
+ 3,
14
+ 3
15
+ ],
16
+ "epsilon_cutoff": 0.0,
17
+ "eta_cutoff": 0.0,
18
+ "length_penalty": 2.0,
19
+ "max_length": 64,
20
+ "min_length": 0,
21
+ "no_repeat_ngram_size": 3,
22
+ "num_assistant_tokens": 20,
23
+ "num_assistant_tokens_schedule": "constant",
24
+ "num_beam_groups": 1,
25
+ "num_beams": 4,
26
+ "num_return_sequences": 1,
27
+ "output_scores": false,
28
+ "pad_token_id": 0,
29
+ "remove_invalid_values": false,
30
+ "repetition_penalty": 1.0,
31
+ "return_dict_in_generate": false,
32
+ "target_lookbehind": 10,
33
+ "temperature": 1.0,
34
+ "top_k": 50,
35
+ "top_p": 1.0,
36
+ "transformers_version": "5.0.0",
37
+ "typical_p": 1.0,
38
+ "use_cache": false
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5baa3bf6079e432500c1b216f7684ea90ba0a61d0296b8dc98cb7abcb0eb7d8a
3
+ size 115436056