commit 1de2328710a0f64b21873709b383a7aaf2b5ca66 Author: ModelHub XC Date: Wed May 13 16:45:45 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: clips/mfaq Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..357cfec --- /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 +*.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 +*.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 +pytorch_model.bin filter=lfs diff=lfs merge=lfs -text +.git/lfs/objects/32/65/32656706e38c4ffb554cd11524a935b5ed31b6685a661db4d802d062a2e34c3c filter=lfs diff=lfs merge=lfs -text +.git/lfs/objects/06/d1/06d1de8984836f80f4d67ad569562fe9836cfbbd185be6fd908a4a43d545e001 filter=lfs diff=lfs merge=lfs -text +.git/lfs/objects/94/cb/94cb37f01aab796c19281c16c74ec08010630bc4b4ec7f84f764bb2ba357b8b9 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..3267343 --- /dev/null +++ b/README.md @@ -0,0 +1,116 @@ +--- +pipeline_tag: sentence-similarity +license: apache-2.0 +language: +- cs +- da +- de +- en +- es +- fi +- fr +- he +- hr +- hu +- id +- it +- nl +- 'no' +- pl +- pt +- ro +- ru +- sv +- tr +- vi +tags: +- sentence-transformers +- feature-extraction +- sentence-similarity +- transformers +datasets: +- clips/mfaq +widget: + source_sentence: "How many models can I host on HuggingFace?" + sentences: + - "All plans come with unlimited private models and datasets." + - "AutoNLP is an automatic way to train and deploy state-of-the-art NLP models, seamlessly integrated with the Hugging Face ecosystem." + - "Based on how much training data and model variants are created, we send you a compute cost and payment link - as low as $10 per job." + +--- + +# MFAQ + +We present a multilingual FAQ retrieval model trained on the [MFAQ dataset](https://huggingface.co/datasets/clips/mfaq), it ranks candidate answers according to a given question. + +## Installation + +``` +pip install sentence-transformers transformers +``` + +## Usage +You can use MFAQ with sentence-transformers or directly with a HuggingFace model. +In both cases, questions need to be prepended with ``, and answers with ``. + +#### Sentence Transformers +```python +from sentence_transformers import SentenceTransformer + +question = "How many models can I host on HuggingFace?" +answer_1 = "All plans come with unlimited private models and datasets." +answer_2 = "AutoNLP is an automatic way to train and deploy state-of-the-art NLP models, seamlessly integrated with the Hugging Face ecosystem." +answer_3 = "Based on how much training data and model variants are created, we send you a compute cost and payment link - as low as $10 per job." + +model = SentenceTransformer('clips/mfaq') +embeddings = model.encode([question, answer_1, answer_3, answer_3]) +print(embeddings) +``` + +#### HuggingFace Transformers + +```python +from transformers import AutoTokenizer, AutoModel +import torch + +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) + +question = "How many models can I host on HuggingFace?" +answer_1 = "All plans come with unlimited private models and datasets." +answer_2 = "AutoNLP is an automatic way to train and deploy state-of-the-art NLP models, seamlessly integrated with the Hugging Face ecosystem." +answer_3 = "Based on how much training data and model variants are created, we send you a compute cost and payment link - as low as $10 per job." + +tokenizer = AutoTokenizer.from_pretrained('clips/mfaq') +model = AutoModel.from_pretrained('clips/mfaq') + +# Tokenize sentences +encoded_input = tokenizer([question, answer_1, answer_3, answer_3], padding=True, truncation=True, return_tensors='pt') + +# Compute token embeddings +with torch.no_grad(): + model_output = model(**encoded_input) + +# Perform pooling. In this case, max pooling. +sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) +``` + +## Training +You can find the training script for the model [here](https://github.com/clips/mfaq). + +## People +This model was developed by [Maxime De Bruyn](https://www.linkedin.com/in/maximedebruyn/), Ehsan Lotfi, Jeska Buhmann and Walter Daelemans. + +## Citation information +``` +@misc{debruyn2021mfaq, + title={MFAQ: a Multilingual FAQ Dataset}, + author={Maxime De Bruyn and Ehsan Lotfi and Jeska Buhmann and Walter Daelemans}, + year={2021}, + eprint={2109.12870}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..d9479d4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1 @@ +{"": 250003, "": 250004, "": 250002} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..3f90f51 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "clips/mfaq", + "architectures": [ + "XLMRobertaModel" + ], + "attention_probs_dropout_prob": 0.1, + "bos_token_id": 0, + "classifier_dropout": null, + "eos_token_id": 2, + "gradient_checkpointing": true, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.25, + "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", + "tokenizer_class": "XLMRobertaTokenizerFast", + "torch_dtype": "float32", + "transformers_version": "4.10.2", + "type_vocab_size": 1, + "use_cache": true, + "vocab_size": 250005 +} diff --git a/config_sentence_transformers.json b/config_sentence_transformers.json new file mode 100644 index 0000000..fe85b29 --- /dev/null +++ b/config_sentence_transformers.json @@ -0,0 +1,7 @@ +{ + "__version__": { + "sentence_transformers": "2.0.0", + "transformers": "4.10.2", + "pytorch": "1.9.0" + } +} \ 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..e942fd5 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4269157ebf5f786ed8478fd1339aaa3fd582c24acebe1f56ca8a6c228df407 +size 1112262449 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..5b0df78 --- /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}, "additional_special_tokens": ["", "", ""]} \ No newline at end of file diff --git a/tf_model.h5 b/tf_model.h5 new file mode 100644 index 0000000..d76b051 --- /dev/null +++ b/tf_model.h5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840cd21152b9d1a5a435331634f529d77500a36bfbc19c8902f8c5a3e485d9de +size 1112450672 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..f58f260 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cb37f01aab796c19281c16c74ec08010630bc4b4ec7f84f764bb2ba357b8b9 +size 9081696 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..da0b6e9 --- /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"}, "additional_special_tokens": ["", "", ""], "model_max_length": 128, "special_tokens_map_file": null, "name_or_path": "output/1024/checkpoint-3000", "tokenizer_class": "XLMRobertaTokenizer"} \ No newline at end of file