Upload model files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+GoNotoCurrent.ttf filter=lfs diff=lfs merge=lfs -text

GoNotoCurrent.ttf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
+size 15645492

README.md

@@ -1,8 +1,53 @@
 ---
-datasets:
-- stefan-it/german-dbmdz-bert-corpus
-language:
-- de
-pipeline_tag: fill-mask
-license: apache-2.0
----
+tags:
+- masked-auto-encoding
+- generated_from_trainer
+model-index:
+- name: pixel-base-german-dbmdz-pixel-0.00015-0-fp32
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# pixel-base-german-dbmdz-pixel-0.00015-0-fp32
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the wikipedia + bookcorpus dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.00015
+- train_batch_size: 256
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- training_steps: 1500000
+- mixed_precision_training: Apex, opt level O1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.5
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.43,
+    "train_loss": 0.1377392346496582,
+    "train_runtime": 935051.3554,
+    "train_samples_per_second": 410.673,
+    "train_steps_per_second": 1.604
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "PIXELForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "cache_dir": "",
+  "decoder_hidden_size": 512,
+  "decoder_intermediate_size": 2048,
+  "decoder_num_attention_heads": 16,
+  "decoder_num_hidden_layers": 8,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "image_size": [
+    16,
+    8464
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "mask_ratio": 0.25,
+  "model_type": "pixel",
+  "norm_pix_loss": true,
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "revision": "main",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_auth_token": ""
+}

preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "do_normalize": false,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "size": [
+    16,
+    8464
+  ]
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75961d2a82829be2aafdac5f00ee15924886c33d176e268a4e629d6ffbc8ce4
+size 449474181

text_renderer_config.json

@@ -0,0 +1,225 @@
+{
+  "background_color": "white",
+  "dpi": 120,
+  "font_color": "black",
+  "font_file": "GoNotoCurrent.ttf",
+  "font_size": 8,
+  "fonts_list": [
+    "Apple Color Emoji",
+    "DejaVu Math TeX Gyre",
+    "DejaVu Sans",
+    "DejaVu Sans Mono",
+    "DejaVu Serif",
+    "Go Noto Current",
+    "Inconsolata",
+    "Monospace",
+    "Noto Fangsong KSS Rotated",
+    "Noto Fangsong KSS Vertical",
+    "Noto Kufi Arabic",
+    "Noto Music",
+    "Noto Naskh Arabic",
+    "Noto Naskh Arabic UI",
+    "Noto Nastaliq Urdu",
+    "Noto Rashi Hebrew",
+    "Noto Sans",
+    "Noto Sans Adlam",
+    "Noto Sans Adlam Unjoined",
+    "Noto Sans Anatolian Hieroglyphs",
+    "Noto Sans Arabic",
+    "Noto Sans Arabic UI",
+    "Noto Sans Armenian",
+    "Noto Sans Avestan",
+    "Noto Sans Balinese",
+    "Noto Sans Bamum",
+    "Noto Sans Bassa Vah",
+    "Noto Sans Batak",
+    "Noto Sans Bengali",
+    "Noto Sans Bengali UI",
+    "Noto Sans Bhaiksuki",
+    "Noto Sans Brahmi",
+    "Noto Sans Buginese",
+    "Noto Sans Buhid",
+    "Noto Sans CJK HK",
+    "Noto Sans CJK JP",
+    "Noto Sans CJK KR",
+    "Noto Sans CJK SC",
+    "Noto Sans CJK TC",
+    "Noto Sans Canadian Aboriginal",
+    "Noto Sans Carian",
+    "Noto Sans Caucasian Albanian",
+    "Noto Sans Chakma",
+    "Noto Sans Cham",
+    "Noto Sans Cherokee",
+    "Noto Sans Chorasmian",
+    "Noto Sans Coptic",
+    "Noto Sans Cuneiform",
+    "Noto Sans Cypriot",
+    "Noto Sans Cypro Minoan",
+    "Noto Sans Deseret",
+    "Noto Sans Devanagari",
+    "Noto Sans Devanagari UI",
+    "Noto Sans Duployan",
+    "Noto Sans Egyptian Hieroglyphs",
+    "Noto Sans Elbasan",
+    "Noto Sans Elymaic",
+    "Noto Sans Ethiopic",
+    "Noto Sans Georgian",
+    "Noto Sans Glagolitic",
+    "Noto Sans Gothic",
+    "Noto Sans Grantha",
+    "Noto Sans Gujarati",
+    "Noto Sans Gujarati UI",
+    "Noto Sans Gunjala Gondi",
+    "Noto Sans Gurmukhi",
+    "Noto Sans Gurmukhi UI",
+    "Noto Sans Hanifi Rohingya",
+    "Noto Sans Hanunoo",
+    "Noto Sans Hatran",
+    "Noto Sans Hebrew",
+    "Noto Sans Hebrew Droid",
+    "Noto Sans Imperial Aramaic",
+    "Noto Sans Indic Siyaq Numbers",
+    "Noto Sans Inscriptional Pahlavi",
+    "Noto Sans Inscriptional Parthian",
+    "Noto Sans Javanese",
+    "Noto Sans Kaithi",
+    "Noto Sans Kannada",
+    "Noto Sans Kannada UI",
+    "Noto Sans Kawi",
+    "Noto Sans Kayah Li",
+    "Noto Sans Kharoshthi",
+    "Noto Sans Khmer",
+    "Noto Sans Khmer UI",
+    "Noto Sans Khojki",
+    "Noto Sans Khudawadi",
+    "Noto Sans Lao",
+    "Noto Sans Lao Looped",
+    "Noto Sans Lao Looped UI",
+    "Noto Sans Lao UI",
+    "Noto Sans Lepcha",
+    "Noto Sans Limbu",
+    "Noto Sans Linear A",
+    "Noto Sans Linear B",
+    "Noto Sans Lisu",
+    "Noto Sans Lycian",
+    "Noto Sans Lydian",
+    "Noto Sans Mahajani",
+    "Noto Sans Malayalam",
+    "Noto Sans Malayalam UI",
+    "Noto Sans Mandaic",
+    "Noto Sans Manichaean",
+    "Noto Sans Marchen",
+    "Noto Sans Masaram Gondi",
+    "Noto Sans Mayan Numerals",
+    "Noto Sans Medefaidrin",
+    "Noto Sans Meetei Mayek",
+    "Noto Sans Mende Kikakui",
+    "Noto Sans Meroitic",
+    "Noto Sans Miao",
+    "Noto Sans Modi",
+    "Noto Sans Mongolian",
+    "Noto Sans Mono",
+    "Noto Sans Mro",
+    "Noto Sans Multani",
+    "Noto Sans Myanmar",
+    "Noto Sans Myanmar UI",
+    "Noto Sans NKo",
+    "Noto Sans NKo Unjoined",
+    "Noto Sans Nabataean",
+    "Noto Sans Nag Mundari",
+    "Noto Sans Nandinagari",
+    "Noto Sans New Tai Lue",
+    "Noto Sans Newa",
+    "Noto Sans Nushu",
+    "Noto Sans Ogham",
+    "Noto Sans Ol Chiki",
+    "Noto Sans Old Hungarian",
+    "Noto Sans Old Italic",
+    "Noto Sans Old North Arabian",
+    "Noto Sans Old Permic",
+    "Noto Sans Old Persian",
+    "Noto Sans Old Sogdian",
+    "Noto Sans Old South Arabian",
+    "Noto Sans Old Turkic",
+    "Noto Sans Oriya",
+    "Noto Sans Osage",
+    "Noto Sans Osmanya",
+    "Noto Sans Pahawh Hmong",
+    "Noto Sans Palmyrene",
+    "Noto Sans Pau Cin Hau",
+    "Noto Sans Phags-Pa",
+    "Noto Sans Phoenician",
+    "Noto Sans Psalter Pahlavi",
+    "Noto Sans Rejang",
+    "Noto Sans Runic",
+    "Noto Sans Samaritan",
+    "Noto Sans Saurashtra",
+    "Noto Sans Sharada",
+    "Noto Sans Shavian",
+    "Noto Sans Siddham",
+    "Noto Sans SignWriting",
+    "Noto Sans Sinhala",
+    "Noto Sans Sinhala UI",
+    "Noto Sans Sogdian",
+    "Noto Sans Sora Sompeng",
+    "Noto Sans Soyombo",
+    "Noto Sans Sundanese",
+    "Noto Sans Syloti Nagri",
+    "Noto Sans Symbols",
+    "Noto Sans Symbols 2",
+    "Noto Sans Syriac",
+    "Noto Sans Syriac Eastern",
+    "Noto Sans Syriac Western",
+    "Noto Sans Tagalog",
+    "Noto Sans Tagbanwa",
+    "Noto Sans Tai Le",
+    "Noto Sans Tai Tham",
+    "Noto Sans Tai Viet",
+    "Noto Sans Takri",
+    "Noto Sans Tamil",
+    "Noto Sans Tamil Supplement",
+    "Noto Sans Tamil UI",
+    "Noto Sans Tangsa",
+    "Noto Sans Telugu",
+    "Noto Sans Telugu UI",
+    "Noto Sans Test",
+    "Noto Sans Thaana",
+    "Noto Sans Thai",
+    "Noto Sans Thai Looped",
+    "Noto Sans Thai Looped UI",
+    "Noto Sans Thai UI",
+    "Noto Sans Tifinagh",
+    "Noto Sans Tifinagh APT",
+    "Noto Sans Tifinagh Adrar",
+    "Noto Sans Tifinagh Agraw Imazighen",
+    "Noto Sans Tifinagh Ahaggar",
+    "Noto Sans Tifinagh Air",
+    "Noto Sans Tifinagh Azawagh",
+    "Noto Sans Tifinagh Ghat",
+    "Noto Sans Tifinagh Hawad",
+    "Noto Sans Tifinagh Rhissa Ixa",
+    "Noto Sans Tifinagh SIL",
+    "Noto Sans Tifinagh Tawellemmet",
+    "Noto Sans Tirhuta",
+    "Noto Sans Ugaritic",
+    "Noto Sans Vai",
+    "Noto Sans Vithkuqi",
+    "Noto Sans Wancho",
+    "Noto Sans Warang Citi",
+    "Noto Sans Yi",
+    "Noto Sans Zanabazar Square",
+    "Noto Traditional Nushu",
+    "Sans",
+    "Serif",
+    "Source Code Pro",
+    "System-ui",
+    "Ubuntu",
+    "Ubuntu Condensed",
+    "Ubuntu Mono"
+  ],
+  "max_seq_length": 529,
+  "pad_size": 3,
+  "pixels_per_patch": 16,
+  "rgb": false,
+  "text_renderer_type": "PangoCairoTextRenderer"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.43,
+    "train_loss": 0.1377392346496582,
+    "train_runtime": 935051.3554,
+    "train_samples_per_second": 410.673,
+    "train_steps_per_second": 1.604
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c01f435556f10ddc7aa85231f023262303da016552d19f955c8c880903dc970
+size 3195