model uploaded.

README.md

@@ -1,3 +1,24 @@
 ---
+language: 
+- tr
+tags:
+- roberta
 license: cc-by-nc-sa-4.0
+datasets:
+- oscar
 ---
+
+# RoBERTa Turkish medium Word-level 16k (uncased)
+
+Pretrained model on Turkish language using a masked language modeling (MLM) objective. The model is uncased. 
+The pretrained corpus is OSCAR's Turkish split, but it is further filtered and cleaned. 
+
+Model architecture is similar to bert-medium (8 layers, 8 heads, and 512 hidden size). Tokenization algorithm is Word-level, which means text is split by white space. Vocabulary size is 16.7k. 
+
+The details can be found at this paper: 
+https://arxiv.org/...
+
+### BibTeX entry and citation info
+```bibtex
+@article{}
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 516,
+  "model_type": "roberta",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 16700
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2726abd29deab1b6d72d9cb6e87b61af2aa6db6b723905578e9cb3e6b2cd93cd
+size 170908971