Upload 7 files

README.md

@@ -1,3 +1,58 @@
----
-license: gpl-3.0
----
+---
+license: gpl-3.0
+language:
+- pl
+pipeline_tag: fill-mask
+widget:
+ - text: "Kartony to inaczej [MASK], które produkowane są z tektury."
+---
+
+# Model Card for KartonBERT_base_cased_v1
+
+
+This is a classic Polish BERT model, trained with MLM task. 
+It comes with a custom ~23k-tokens BWPT tokenizer. While not ideal, 
+it performs well on certain downstream tasks and serves as a checkpoint in my work.
+
+## Model Description
+
+
+- **Developed by:** Bartłomiej Orlik, https://www.linkedin.com/in/bartłomiej-orlik/
+- **Model type:** pretrained BERT base cased (~23k tokenizer)
+- **Language:** Polish
+- **License:** GPL-3.0
+
+
+## How to use model for fill-mask task
+
+Use the code below to get started with the model.
+```python
+from transformers import pipeline
+
+tokenizer_kwargs={'truncation': True, 'max_length': 512}
+model = pipeline('fill-mask', model='OrlikB/KartonBERT_base_uncased_v1', tokenizer_kwargs=tokenizer_kwargs)
+
+model("Kartony to inaczej [MASK], które produkowane są z tektury.")
+
+# Output
+[{'score': 0.12927177548408508,
+  'token': 5324,
+  'token_str': 'materiały',
+  'sequence': 'kartony to inaczej materiały, które produkowane są z tektury.'},
+ {'score': 0.0821441262960434,
+  'token': 2403,
+  'token_str': 'produkty',
+  'sequence': 'kartony to inaczej produkty, które produkowane są z tektury.'},
+ {'score': 0.06760794669389725,
+  'token': 392,
+  'token_str': 'te',
+  'sequence': 'kartony to inaczej te, które produkowane są z tektury.'},
+ {'score': 0.06753358244895935,
+  'token': 20289,
+  'token_str': 'pudełka',
+  'sequence': 'kartony to inaczej pudełka, które produkowane są z tektury.'},
+ {'score': 0.04844100773334503,
+  'token': 16715,
+  'token_str': 'wyroby',
+  'sequence': 'kartony to inaczej wyroby, które produkowane są z tektury.'}]
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "KartonBERT_base_uncased_v1",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 23000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e99e92f0c84fcc5a2ab752896108db731da4d26438c3881cd08f0318be3a484
+size 414943200

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": false,
+  "tokenize_chinese_chars": false,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}