commit 193dd355901b76437babf7677d59837dea694586 Author: ModelHub XC Date: Thu Jul 30 01:36:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: meedan/paraphrase-filipino-mpnet-base-v2 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a8f6805 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,29 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.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 +*.zstandard filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json 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..a39268d --- /dev/null +++ b/README.md @@ -0,0 +1,134 @@ +--- +pipeline_tag: sentence-similarity +tags: +- sentence-transformers +- feature-extraction +- sentence-similarity +- transformers +--- + +# paraphrase-filipino-mpnet-base-v2 + +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. + +This model was trained using the student--teacher approach outlined in [Reimers and Gurevych (2020)](https://aclanthology.org/2020.emnlp-main.365/). + +The teacher model was [sentence-transformers/paraphrase-mpnet-base-v2](), and the student model was [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](), which is based on XLM-R. We trained the model for 2 epoch using a batch size of 64 on parallel data English--Tagalog and English--Filipino data from OPUS. We found the data to be of variable quality and filtered it to only include sentence pairs that the Compact Language Detection kit (CLDv3) identified reliably as being in Tagalog or Filipino. Other parameters were left unchanged from the example [make_multilingual_sys.py](https://github.com/UKPLab/sentence-transformers/blob/master/examples/training/multilingual/make_multilingual_sys.py) code in the sentence-transformers code base. + +## 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 +from scipy.spatial import distance +import itertools + +model = SentenceTransformer('meedan/paraphrase-filipino-mpnet-base-v2') + +sentences = ["saan pong mga lugar available ang pfizer vaccine? Thank you!","Ask ko lang po saan meron available na vaccine","Where is the vaccine available?"] +embeddings = model.encode(sentences) +dist=[distance.cosine(i,j) for i,j in itertools.combinations(embeddings,2)] +print(dist) +``` + + + +## 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('{MODEL_NAME}') +model = AutoModel.from_pretrained('{MODEL_NAME}') + +# Tokenize sentences +encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') + +# Compute token embeddings +with torch.no_grad(): + model_output = model(**encoded_input) + +# Perform pooling. In this case, mean pooling. +sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) + +print("Sentence embeddings:") +print(sentence_embeddings) +``` + + + +## Evaluation Results + +We machine translated the STS data from [SentEval](https://github.com/facebookresearch/SentEval) to Filipino using the Google Translation API and used this for evaluation alongside the original English-language STS data. We used Spearman's rank correlation coefficient. We found roughly the same performance as the original base model (sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on English while substantial gains were made for Filipino. For English, the average correlation is 0.80. For Filipino, it is 0.75. + + +For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME}) + + +## Training +The model was trained with the parameters: + +**DataLoader**: + +`torch.utils.data.dataloader.DataLoader` of length 79097 with parameters: +``` +{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} +``` + +**Loss**: + +`sentence_transformers.losses.MSELoss.MSELoss` + +Parameters of the fit()-Method: +``` +{ + "epochs": 2, + "evaluation_steps": 0, + "evaluator": "NoneType", + "max_grad_norm": 1, + "optimizer_class": "", + "optimizer_params": { + "correct_bias": false, + "eps": 1e-06, + "lr": 2e-05 + }, + "scheduler": "WarmupLinear", + "steps_per_epoch": null, + "warmup_steps": 10000, + "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 + + \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..1bbd36b --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2", + "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": "4.17.0", + "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..102be5f --- /dev/null +++ b/config_sentence_transformers.json @@ -0,0 +1,7 @@ +{ + "__version__": { + "sentence_transformers": "2.2.0", + "transformers": "4.17.0", + "pytorch": "1.10.0" + } +} \ No newline at end of file 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..91d9174 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca9752cfe5545d2487ce6cc6de6fb5ec835a03f711dfa1b7a6f16428672983e +size 1112256881 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..2ea7ad0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{"bos_token": "", "eos_token": "", "unk_token": "", "sep_token": "", "pad_token": "", "cls_token": "", "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..b0b95de --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60b6b43406a48bf3638526314f3d232d97058bc93472ff2de930d43686fa441 +size 17082913 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..2efdf09 --- /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": null, "name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2", "tokenizer_class": "XLMRobertaTokenizer"} \ No newline at end of file