initial release

README.md

@@ -0,0 +1,26 @@
+---
+language:
+- "th"
+tags:
+- "thai"
+- "masked-lm"
+base_model: clicknext/phayathaibert
+license: "apache-2.0"
+pipeline_tag: "fill-mask"
+mask_token: "<mask>"
+---
+
+# camembert-thai-base
+
+## Model Description
+
+This is a CamemBERT model pre-trained on Thai texts, derived from [PhayaThaiBERT](https://huggingface.co/clicknext/phayathaibert) with the tokenizer improved. You can fine-tune `camembert-thai-base` for downstream tasks, such as [POS-tagging](https://huggingface.co/KoichiYasuoka/camembert-thai-base-upos), [dependency-parsing](https://huggingface.co/KoichiYasuoka/camembert-thai-base-ud-goeswith), and so on.
+
+## How to Use
+
+```py
+from transformers import AutoTokenizer,AutoModelForMaskedLM
+tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/camembert-thai-base")
+model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/camembert-thai-base")
+```
+

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "CamembertForMaskedLM"
+  ],
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 249262
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ddb1786f3b22021ff636938d898203fcfe33381b15a63f72b65bdfd375520e4
+size 1110969209

special_tokens_map.json

@@ -0,0 +1,56 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d187215f962d5cce64e220651641808a1afeb332d7c6e22447bfe9b2aa9138
+size 16916048