Upload folder using huggingface_hub

config.json

@@ -0,0 +1,104 @@
+{
+  "_name_or_path": "pythainlp/thainer-corpus-v2-base-model",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-PERSON",
+    "1": "I-PERSON",
+    "2": "O",
+    "3": "B-ORGANIZATION",
+    "4": "B-LOCATION",
+    "5": "I-ORGANIZATION",
+    "6": "I-LOCATION",
+    "7": "B-DATE",
+    "8": "I-DATE",
+    "9": "B-TIME",
+    "10": "I-TIME",
+    "11": "B-MONEY",
+    "12": "I-MONEY",
+    "13": "B-FACILITY",
+    "14": "I-FACILITY",
+    "15": "B-URL",
+    "16": "I-URL",
+    "17": "B-PERCENT",
+    "18": "I-PERCENT",
+    "19": "B-LEN",
+    "20": "I-LEN",
+    "21": "B-AGO",
+    "22": "I-AGO",
+    "23": "B-LAW",
+    "24": "I-LAW",
+    "25": "B-PHONE",
+    "26": "I-PHONE",
+    "27": "B-EMAIL",
+    "28": "I-EMAIL",
+    "29": "B-ZIP",
+    "30": "B-TEMPERATURE",
+    "31": "I-TEMPERATURE",
+    "32": "B-DTAE",
+    "33": "I-DTAE",
+    "34": "B-DATA",
+    "35": "I-DATA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGO": 21,
+    "B-DATA": 34,
+    "B-DATE": 7,
+    "B-DTAE": 32,
+    "B-EMAIL": 27,
+    "B-FACILITY": 13,
+    "B-LAW": 23,
+    "B-LEN": 19,
+    "B-LOCATION": 4,
+    "B-MONEY": 11,
+    "B-ORGANIZATION": 3,
+    "B-PERCENT": 17,
+    "B-PERSON": 0,
+    "B-PHONE": 25,
+    "B-TEMPERATURE": 30,
+    "B-TIME": 9,
+    "B-URL": 15,
+    "B-ZIP": 29,
+    "I-AGO": 22,
+    "I-DATA": 35,
+    "I-DATE": 8,
+    "I-DTAE": 33,
+    "I-EMAIL": 28,
+    "I-FACILITY": 14,
+    "I-LAW": 24,
+    "I-LEN": 20,
+    "I-LOCATION": 6,
+    "I-MONEY": 12,
+    "I-ORGANIZATION": 5,
+    "I-PERCENT": 18,
+    "I-PERSON": 1,
+    "I-PHONE": 26,
+    "I-TEMPERATURE": 31,
+    "I-TIME": 10,
+    "I-URL": 16,
+    "O": 2
+  },
+  "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": "4.34.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 25005
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed8e1d616da91ce844a96f4eee86d489933a5eebfc0897965dccb8a2054aa85
+size 419007377

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba8681058b6cbcf93c900a83e683a753b744325ac14688be3c417c668fa56c5
+size 105930674

quantize_config.json

@@ -0,0 +1,36 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "CumSum",
+                "Gather",
+                "Not",
+                "Pow",
+                "Concat",
+                "Erf",
+                "ReduceMean",
+                "Softmax",
+                "Mul",
+                "Where",
+                "Slice",
+                "MatMul",
+                "Sqrt",
+                "Unsqueeze",
+                "Shape",
+                "Reshape",
+                "Sub",
+                "Add",
+                "Div",
+                "Equal",
+                "ConstantOfShape",
+                "Cast",
+                "Constant",
+                "Expand",
+                "Transpose"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
+size 904693

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}