初始化项目，由ModelHub XC社区提供模型

Model: kornwtp/ConGen-simcse-model-roberta-base-thai
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+pipeline_tag: sentence-similarity
+license: apache-2.0
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+---
+
+# kornwtp/ConGen-simcse-model-roberta-base-thai
+
+This is a [ConGen](https://github.com/KornWtp/ConGen) model: It maps sentences to a 768 dimensional dense vector space and can be used for tasks like semantic search.
+
+
+
+## Usage
+
+Using this model becomes easy when you have [ConGen](https://github.com/KornWtp/ConGen) installed:
+
+```
+pip install -U git+https://github.com/KornWtp/ConGen.git
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["กลุ่มผู้ชายเล่นฟุตบอลบนชายหาด", "กลุ่มเด็กชายกำลังเล่นฟุตบอลบนชายหาด"]
+
+model = SentenceTransformer('kornwtp/ConGen-simcse-model-roberta-base-thai')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Evaluation Results
+
+
+
+For an automated evaluation of this model, see the *Thai Sentence Embeddings Benchmark*: [Semantic Textual Similarity](https://github.com/KornWtp/ConGen#thai-semantic-textual-similarity-benchmark)
+
+
+## Citing & Authors
+
+```bibtex 
+@inproceedings{limkonchotiwat-etal-2022-congen,
+    title = "{ConGen}: Unsupervised Control and Generalization Distillation For Sentence Representation",
+    author = "Limkonchotiwat, Peerat  and
+      Ponwitayarat, Wuttikorn  and
+      Lowphansirikul, Lalita and
+      Udomcharoenchaikit, Can  and
+      Chuangsuwanich, Ekapol  and
+      Nutanong, Sarana",
+    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
+    year = "2022",
+    publisher = "Association for Computational Linguistics",
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "../../seeder-sbert/pretrain-models/wangchanberta-base-att-spm-uncased",
+  "architectures": [
+    "CamembertModel"
+  ],
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 25005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afea29fbbd81463e32d3807d316b0d5a7459a0c03daa043aa86f458c9c1d8172
+size 421064183

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED", "<_>"], "special_tokens_map_file": null, "name_or_path": "../../seeder-sbert/pretrain-models/wangchanberta-base-att-spm-uncased", "sp_model_kwargs": {}, "tokenizer_class": "CamembertTokenizer"}