commit 5a1e7e46981871fce08009ce1b6eb8fab6e527ba Author: ModelHub XC Date: Mon Jul 20 18:28:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: kornwtp/ConGen-Multilingual-MiniLM-L12 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..637fa16 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,32 @@ +*.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 +*.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 +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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6be15ef --- /dev/null +++ b/README.md @@ -0,0 +1,60 @@ +--- +pipeline_tag: sentence-similarity +license: apache-2.0 +tags: +- sentence-transformers +- feature-extraction +- sentence-similarity +- transformers +--- + +# kornwtp/ConGen-Multilingual-MiniLM-L12 + +This is a [ConGen](https://github.com/KornWtp/ConGen) model: It maps sentences to a 384 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 = ["This is an example sentence", "Each sentence is converted"] + +model = SentenceTransformer('kornwtp/ConGen-Multilingual-MiniLM-L12') +embeddings = model.encode(sentences) +print(embeddings) +``` + + + +## Evaluation Results + + + +For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [Semantic Textual Similarity](https://github.com/KornWtp/ConGen#main-results---sts) + + +## 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", +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..4198f9a --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "pretrianed_models/Multilingual-MiniLM-L12-H384", + "architectures": [ + "BertModel" + ], + "attention_probs_dropout_prob": 0.1, + "classifier_dropout": null, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 384, + "initializer_range": 0.02, + "intermediate_size": 1536, + "layer_norm_eps": 1e-12, + "max_position_embeddings": 512, + "model_type": "bert", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "pad_token_id": 0, + "position_embedding_type": "absolute", + "tokenizer_class": "XLMRobertaTokenizer", + "torch_dtype": "float32", + "transformers_version": "4.12.5", + "type_vocab_size": 2, + "use_cache": true, + "vocab_size": 250037 +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..fea5362 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a374d0343d784c2366d3ea3f34ed670367d2b3cfa5ed9b06481e92459d4620bd +size 470701623 diff --git a/sentence_bert_config.json b/sentence_bert_config.json new file mode 100644 index 0000000..5fd1042 --- /dev/null +++ b/sentence_bert_config.json @@ -0,0 +1,4 @@ +{ + "max_seq_length": 128, + "do_lower_case": false +} \ No newline at end of file diff --git a/sentencepiece.bpe.model b/sentencepiece.bpe.model new file mode 100644 index 0000000..7a3f40a --- /dev/null +++ b/sentencepiece.bpe.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865 +size 5069051 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..6cd1d90 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{"bos_token": "", "eos_token": "", "unk_token": "", "sep_token": "", "pad_token": "", "cls_token": "", "mask_token": ""} \ No newline at end of file diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..569ddfd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"bos_token": "", "eos_token": "", "sep_token": "", "cls_token": "", "unk_token": "", "pad_token": "", "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": "/ist/users/wuttikornp/.cache/torch/sentence_transformers/microsoft_Multilingual-MiniLM-L12-H384/special_tokens_map.json", "name_or_path": "pretrianed_models/Multilingual-MiniLM-L12-H384", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"} \ No newline at end of file