release: v0.1.0

README.md

@@ -0,0 +1,22 @@
+---
+language: da
+license: cc-by-4.0
+---
+
+# Danish ConvBERT medium small (cased)
+
+[ConvBERT](https://arxiv.org/abs/2008.02496) model pretrained on a custom Danish corpus (~17.5gb). 
+For details regarding data sources and training procedure, along with benchmarks on downstream tasks, go to: https://github.com/sarnikowski/danish_transformers 
+
+## Usage
+
+```python
+from transformers import ConvBertTokenizer, ConvBertModel
+
+tokenizer = ConvBertTokenizer.from_pretrained("sarnikowski/convbert-medium-small-da-cased")
+model = ConvBertModel.from_pretrained("sarnikowski/convbert-medium-small-da-cased")
+```
+
+## Questions?
+
+If you have any questions feel free to open an issue on the [danish_transformers](https://github.com/sarnikowski/danish_transformers) repository, or send an email to p.sarnikowski@gmail.com

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": ".",
+  "architectures": [
+    "ConvBertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "conv_kernel_size": 9,
+  "directionality": "bidi",
+  "embedding_size": 128,
+  "eos_token_id": 2,
+  "head_ratio": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "convbert",
+  "num_attention_heads": 6,
+  "num_groups": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "transformers_version": "4.4.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 28995,
+  "xla_device": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61cd892669eb1d6bba3976b8a49d58e9a059edab96f39d0e5616c60ebf40093b
+size 98069041

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d028bef548d25b1411c294a78bb0f750a13e0f170431d7df968faec57dff7599
+size 97709952

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false}