2nd version + model cards addition

README.md

@@ -0,0 +1,21 @@
+# ByT5 Dutch OCR correction 
+
+This model is a finetuned byT5 model that corrects OCR mistakes found in dutch sentences. The [google/byt5-base](https://huggingface.co/google/byt5-base) model is finetuned on the dutch section of the [OSCAR](https://huggingface.co/datasets/oscar) dataset. 
+
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, T5ForConditionalGeneration
+
+example_sentence = "Een algoritme dat op basis van kunstmatige inte11i9entie vkijwe1 geautomatiseerd een Nederlandstalige tekst samenstelt."
+
+tokenizer = AutoTokenizer.from_pretrained('ml6team/byt5-small-dutch-ocr-correction')
+
+model_inputs = tokenizer(example_sentence, max_length=128, truncation=True, return_tensors="pt")
+
+model = T5ForConditionalGeneration.from_pretrained('ml6team/byt5-small-dutch-ocr-correction')
+outputs = model.generate(**model_inputs, max_length=128)
+
+tokenizer.decode(outputs[0])
+```

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "google/byt5-small",
+  "_name_or_path": "google/byt5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 3584,
+  "d_ff": 3968,
   "d_kv": 64,
-  "d_model": 1472,
+  "d_model": 1536,
   "decoder_start_token_id": 0,
   "dropout_rate": 0.1,
   "eos_token_id": 1,
@@ -14,10 +14,12 @@
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
   "layer_norm_epsilon": 1e-06,
+  "max_length": 128,
   "model_type": "t5",
-  "num_decoder_layers": 4,
-  "num_heads": 6,
-  "num_layers": 12,
+  "num_decoder_layers": 6,
+  "num_heads": 12,
+  "num_layers": 18,
+  "output_past": true,
   "pad_token_id": 0,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2f9fdf11711ba5274f54d5648662b8ce92fbd0db1292c4e4b5cdaafc448e59a
-size 1198627501
+oid sha256:27f964d9bdf1133ea53987a2309ea0a1aa395c8469a14ea157524c9a326f1f14
+size 2326726857

tokenizer_config.json

@@ -1 +1 @@
-{"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "extra_ids": 125, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>", "<extra_id_100>", "<extra_id_101>", "<extra_id_102>", "<extra_id_103>", "<extra_id_104>", "<extra_id_105>", "<extra_id_106>", "<extra_id_107>", "<extra_id_108>", "<extra_id_109>", "<extra_id_110>", "<extra_id_111>", "<extra_id_112>", "<extra_id_113>", "<extra_id_114>", "<extra_id_115>", "<extra_id_116>", "<extra_id_117>", "<extra_id_118>", "<extra_id_119>", "<extra_id_120>", "<extra_id_121>", "<extra_id_122>", "<extra_id_123>", "<extra_id_124>"], "special_tokens_map_file": "/home/jupyter/.cache/huggingface/transformers/3715c3de7f5eda8f5c9274c55ea8e8632fe6e4cdfdf8e9066ae173b956cd9b80.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109", "tokenizer_file": null, "name_or_path": "google/byt5-small", "tokenizer_class": "ByT5Tokenizer"}
+{"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "extra_ids": 125, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>", "<extra_id_100>", "<extra_id_101>", "<extra_id_102>", "<extra_id_103>", "<extra_id_104>", "<extra_id_105>", "<extra_id_106>", "<extra_id_107>", "<extra_id_108>", "<extra_id_109>", "<extra_id_110>", "<extra_id_111>", "<extra_id_112>", "<extra_id_113>", "<extra_id_114>", "<extra_id_115>", "<extra_id_116>", "<extra_id_117>", "<extra_id_118>", "<extra_id_119>", "<extra_id_120>", "<extra_id_121>", "<extra_id_122>", "<extra_id_123>", "<extra_id_124>"], "max_length": 128, "special_tokens_map_file": "/home/jupyter/.cache/huggingface/transformers/f22e687c418a9ed3e651ca340d6a5880bbb312bc24bbe893f5cd47288891b89d.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109", "tokenizer_file": null, "name_or_path": "google/byt5-base", "tokenizer_class": "ByT5Tokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3e2f55c734f8bf61615c7f29f6bcf32b44d99e6e8b7b5d9dd96d470107c35f6
+oid sha256:f8b7c3480a155bfb2b1502ff18aa4ae2e2e6456fef905f4c4cf747423c8947df
 size 2671