Add model weightsand tokenizer, wangchanberta-base-wiki-20210520-spm checkpoint @25k steps

.gitattributes

@@ -0,0 +1,2 @@
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "camembert",
+  "num_attention_head": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 24005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1581460a3720d19cfc55e0ba783d2efe3122976fc43d87387c116a8842046202
+size 209055553

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7116aaab4c6acde0efa89ef8a6c2df4246c0a3c4f64b9b4f4ac70bd43457cd3
+size 980969

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+    "bos_token": "<s>",
+    "eos_token": "</s>",
+    "unk_token": "<unk>",
+    "sep_token": "</s>",
+    "cls_token": "<s>",
+    "pad_token": "<pad>",
+    "mask_token": "<mask>",
+    "additional_special_tokens": [
+        "<s>NOTUSED",
+        "</s>NOTUSED",
+        "▁"
+    ]
+}