commit b09c32722d5a7d5e2d779d644c41905ba14c368a Author: ModelHub XC Date: Mon Aug 17 13:41:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: BlackKakapo/stsb-xlm-r-multilingual-ro Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4867779 --- /dev/null +++ b/.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 +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/1_Pooling/config.json b/1_Pooling/config.json new file mode 100644 index 0000000..4e09f29 --- /dev/null +++ b/1_Pooling/config.json @@ -0,0 +1,7 @@ +{ + "word_embedding_dimension": 768, + "pooling_mode_cls_token": false, + "pooling_mode_mean_tokens": true, + "pooling_mode_max_tokens": false, + "pooling_mode_mean_sqrt_len_tokens": false +} \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..fe693c4 --- /dev/null +++ b/README.md @@ -0,0 +1,121 @@ +--- +pipeline_tag: sentence-similarity +tags: +- sentence-transformers +- feature-extraction +- sentence-similarity +- transformers +language: +- ro +language_creators: +- machine-generated +dataset: +- ro_sts + +--- + +# stsb-xlm-r-multilingual-ro + +This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. Fine Tune of stsb-xlm-r-multilingual for romanian language + + + +## Usage (Sentence-Transformers) + +Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: + +``` +pip install -U sentence-transformers +``` + +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('BlackKakapo/stsb-xlm-r-multilingual-ro') +embeddings = model.encode(sentences) +print(embeddings) +``` + + + +## Usage (HuggingFace Transformers) +Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. + +```python +from transformers import AutoTokenizer, AutoModel +import torch + + +#Mean Pooling - Take attention mask into account for correct averaging +def mean_pooling(model_output, attention_mask): + token_embeddings = model_output[0] #First element of model_output contains all token embeddings + input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() + return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) + + +# Sentences we want sentence embeddings for +sentences = ['This is an example sentence', 'Each sentence is converted'] + +# Load model from HuggingFace Hub +tokenizer = AutoTokenizer.from_pretrained('BlackKakapo/stsb-xlm-r-multilingual-ro') +model = AutoModel.from_pretrained('BlackKakapo/stsb-xlm-r-multilingual-ro') +``` + +## Training +**DataSet**: +[STS-ro](https://www.SBERT.net) +The text dataset is in Romanian (ro). Score is from 0 to 5, that why I divide score by 5, becouse the score for EmbeddingSimilarityEvaluator (evaluator for finetune) need to be from 0 to 1. +Dataset Structure: +``` +{ +'score': 1.5, + 'sentence1': 'Un bărbat cântă la harpă.', + 'sentence2': 'Un bărbat cântă la claviatură.', +} +``` + + +**DataLoader**: + +`torch.utils.data.dataloader.DataLoader` of length 223 with parameters: +``` +{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} +``` + +**Loss**: + +`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` + +Parameters of the fit()-Method: +``` +{ + "epochs": 10, + "evaluation_steps": 0, + "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator", + "max_grad_norm": 1, + "optimizer_class": "", + "optimizer_params": { + "lr": 2e-05 + }, + "scheduler": "WarmupLinear", + "steps_per_epoch": null, + "warmup_steps": 100, + "weight_decay": 0.01 +} +``` + + +## Full Model Architecture +``` +SentenceTransformer( + (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel + (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False}) +) +``` + +## Citing & Authors + +# BlackKakapo diff --git a/config.json b/config.json new file mode 100644 index 0000000..f9a08ee --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "stsb-xlm-r-multilingual-ro\\", + "architectures": [ + "XLMRobertaModel" + ], + "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, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 514, + "model_type": "xlm-roberta", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "output_past": true, + "pad_token_id": 1, + "position_embedding_type": "absolute", + "torch_dtype": "float32", + "transformers_version": "4.16.2", + "type_vocab_size": 1, + "use_cache": true, + "vocab_size": 250002 +} diff --git a/config_sentence_transformers.json b/config_sentence_transformers.json new file mode 100644 index 0000000..b974b34 --- /dev/null +++ b/config_sentence_transformers.json @@ -0,0 +1,7 @@ +{ + "__version__": { + "sentence_transformers": "2.0.0", + "transformers": "4.7.0", + "pytorch": "1.9.0+cu102" + } +} \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..b8a6d0f --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878afaa86c38f520ff2cd8ed3d4162ae16ed450068621ae04c6fa137826a1433 +size 1112201288 diff --git a/modules.json b/modules.json new file mode 100644 index 0000000..f7640f9 --- /dev/null +++ b/modules.json @@ -0,0 +1,14 @@ +[ + { + "idx": 0, + "name": "0", + "path": "", + "type": "sentence_transformers.models.Transformer" + }, + { + "idx": 1, + "name": "1", + "path": "1_Pooling", + "type": "sentence_transformers.models.Pooling" + } +] \ No newline at end of file diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..3eba4b1 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85c540fb89d07480fdc3618906d23243d68c0a95b42ef286e111b3a9382a2e8e +size 1112255985 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.json b/tokenizer.json new file mode 100644 index 0000000..2207fda --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40e4a12784b3e7ee5c5c373c28a22f02497b30a4ea39d9548ee0f3c6a31e9ca9 +size 17082983 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..e6a1441 --- /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"}, "model_max_length": 512, "special_tokens_map_file": "output/xlm-r-nli-stsb-40langs/0_Transformer/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "stsb-xlm-r-multilingual-ro\\", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"} \ No newline at end of file