Hugging Face's logo

ufal
/
byt5-base-geccc-mate

Text Generation
Transformers
PyTorch
TensorFlow
Safetensors
Czech
t5
text2text-generation
Czech
GEC
GECCC dataset
text-generation-inference
Model card Files
xet
Community
1
foxik commited on
Commit
c035918
·
verified ·
1 Parent(s): a1b67f7

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. README.md +82 -0
  2. config.json +33 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +150 -0
  7. tf_model.h5 +3 -0
  8. tokenizer_config.json +155 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: cs
3
+ license: cc-by-nc-sa-4.0
4
+ tags:
5
+ - Czech
6
+ - GEC
7
+ - GECCC dataset
8
+ base_model: google/byt5-base
9
+ ---
10
+
11
+ # Model Card for byt5-base-geccc-mate
12
+
13
+ The `byt5-base-geccc-mate` model is a sequence-to-sequence model performing
14
+ grammar error correction in Czech described in the paper
15
+ [Refining Czech GEC: Insights from a Multi-Experiment Approach](https://arxiv.org/abs/2506.22402).
16
+ It is a finetuned version of [byt5-base](https://huggingface.co/google/byt5-base) using
17
+ the MATE method and the [GECCC dataset](https://hdl.handle.net/11234/1-4861).
18
+
19
+ ## Model Description
20
+
21
+ - **Developed by:** [Seznam.cz](https://seznam.cz) and [Charles University, MFF, ÚFAL](https://ufal.mff.cuni.cz/)
22
+ - **Language(s) (NLP):** Czech
23
+ - **Model type:** character-based encoder-decoder Transformer model
24
+ - **Finetuned from model:** `google/byt5-base`
25
+ - **Finetuned on:**
26
+ - first synthetic errors generated by the MATE method (see [the paper](https://arxiv.org/abs/2506.22402))
27
+ - then the [GECCC dataset](https://hdl.handle.net/11234/1-4861)
28
+ - **License:** CC BY-NC-SA 4.0
29
+
30
+ ## Model Sources
31
+
32
+ - **Repository:** https://github.com/ufal/tsd2025-gec
33
+ - **Paper:** [Refining Czech GEC: Insights from a Multi-Experiment Approach](https://arxiv.org/abs/2506.22402)
34
+ - **Dataset:** [GECCC dataset](https://hdl.handle.net/11234/1-4861)
35
+
36
+ ## Evaluation
37
+
38
+ <div align="center">
39
+ <img src="https://github.com/ufal/tsd2025-gec/blob/main/figures/bubble_chart.svg?raw=true" width="100%" alt="Performance bubblechart" />
40
+ </div>
41
+
42
+ | Model | Parameters | GECCC F-0.5 score |
43
+ |:------|-----------:|:-----------------:|
44
+ | [byt5-small-geccc-mate](https://hf.co/ufal/byt5-small-geccc-mate) | 300M | 72.56 |
45
+ | [**byt5-base-geccc-mate**](https://hf.co/ufal/byt5-base-geccc-mate) | **582M** | **75.15** |
46
+ | [byt5-large-geccc-mate](https://hf.co/ufal/byt5-large-geccc-mate) | 1275M | 77.01 |
47
+ | [transformer-base-geccc-mate](https://hf.co/ufal/transformer-base-geccc-mate) | 65M | 73.73 |
48
+
49
+ ## Uses
50
+
51
+ The model can be directly used to process space-tokenized input Czech text and produce grammar-corrected Czech text.
52
+
53
+ ## How to Get Started with the Model
54
+
55
+ Use the code below to get started with the model. Note that the input must be **space-tokenized**, i.e., every token (using the [UDPipe 1](https://ufal.mff.cuni.cz/udpipe/1) tokenizer [czech-pdt-ud-2.5-191206.udpipe](https://hdl.handle.net/11234/1-3131)) must be space-separated.
56
+
57
+ ```python
58
+ tokenizer = transformers.AutoTokenizer.from_pretrained("ufal/byt5-base-geccc-mate")
59
+ model = transformers.AutoModelForSeq2SeqLM.from_pretrained("ufal/byt5-base-geccc-mate")
60
+
61
+ batch = tokenizer(["Sveřepý šakali zavile vyly na býlí mesýc .", return_tensors="pt")
62
+ outputs = model.generate(batch.input_ids, max_length=256, num_beams=4)
63
+
64
+ print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
65
+ ```
66
+
67
+ ## BibTeX Citation
68
+
69
+ ```
70
+ @InProceedings{10.1007/978-3-032-02551-7_7,
71
+ author="Pechman, Petr and Straka, Milan and Strakov{\'a}, Jana and N{\'a}plava, Jakub",
72
+ editor="Ek{\v{s}}tein, Kamil and Konop{\'i}k, Miloslav and Pra{\v{z}}{\'a}k, Ond{\v{r}}ej and P{\'a}rtl, Franti{\v{s}}ek",
73
+ title="Refining Czech GEC: Insights from a Multi-experiment Approach",
74
+ booktitle="Text, Speech, and Dialogue",
75
+ year="2026",
76
+ publisher="Springer Nature Switzerland",
77
+ address="Cham",
78
+ pages="64--76",
79
+ isbn="978-3-032-02551-7",
80
+ doi="10.1007/978-3-032-02551-7_7"
81
+ }
82
+ ```
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 3968,
7
+ "d_kv": 64,
8
+ "d_model": 1536,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "gradient_checkpointing": false,
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "num_decoder_layers": 6,
21
+ "num_heads": 12,
22
+ "num_layers": 18,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "ByT5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.33.3",
31
+ "use_cache": true,
32
+ "vocab_size": 384
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.33.3"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7986a617559a1b16ca23bc84befcba592f1ee63a05f0d38a819a6b0ab543cee0
3
+ size 2326643632
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821159f494a0bf63fd9a4a0bbb619feccfea005095b9668fe35aed3adeac63db
3
+ size 2326697363
special_tokens_map.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>",
119
+ "<extra_id_116>",
120
+ "<extra_id_117>",
121
+ "<extra_id_118>",
122
+ "<extra_id_119>",
123
+ "<extra_id_120>",
124
+ "<extra_id_121>",
125
+ "<extra_id_122>",
126
+ "<extra_id_123>",
127
+ "<extra_id_124>"
128
+ ],
129
+ "eos_token": {
130
+ "content": "</s>",
131
+ "lstrip": false,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ "pad_token": {
137
+ "content": "<pad>",
138
+ "lstrip": false,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ "unk_token": {
144
+ "content": "<unk>",
145
+ "lstrip": false,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ }
150
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f376f35b566742249f456b774c7cefec48a03f6bfbc9ba535ff435e111140d
3
+ size 2331850272
tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>",
119
+ "<extra_id_116>",
120
+ "<extra_id_117>",
121
+ "<extra_id_118>",
122
+ "<extra_id_119>",
123
+ "<extra_id_120>",
124
+ "<extra_id_121>",
125
+ "<extra_id_122>",
126
+ "<extra_id_123>",
127
+ "<extra_id_124>"
128
+ ],
129
+ "eos_token": {
130
+ "__type": "AddedToken",
131
+ "content": "</s>",
132
+ "lstrip": false,
133
+ "normalized": true,
134
+ "rstrip": false,
135
+ "single_word": false
136
+ },
137
+ "extra_ids": 125,
138
+ "pad_token": {
139
+ "__type": "AddedToken",
140
+ "content": "<pad>",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false
145
+ },
146
+ "tokenizer_class": "ByT5Tokenizer",
147
+ "unk_token": {
148
+ "__type": "AddedToken",
149
+ "content": "<unk>",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false
154
+ }
155
+ }