tuna2134/sbv2-v2
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Improve: Support ONNX inference, add ONNX conversion script

Browse Source
This commit is contained in:
tsukumi
2024-09-17 16:55:03 +09:00
parent f42b9f0f89
commit 5e2c83c6c7
21 changed files with 44483 additions and 376 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
bert/chinese-roberta-wwm-ext-large/.gitattributes vendored
View File

@@ -1,9 +0,0 @@
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tar.gz filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text

57
bert/chinese-roberta-wwm-ext-large/README.md
View File

@@ -1,57 +0,0 @@
---
language:
- zh
tags:
- bert
license: "apache-2.0"
---
# Please use 'Bert' related functions to load this model!
## Chinese BERT with Whole Word Masking
For further accelerating Chinese natural language processing, we provide **Chinese pre-trained BERT with Whole Word Masking**.
**[Pre-Training with Whole Word Masking for Chinese BERT](https://arxiv.org/abs/1906.08101)**
Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Ziqing Yang, Shijin Wang, Guoping Hu
This repository is developed based on：https://github.com/google-research/bert
You may also interested in,
- Chinese BERT series: https://github.com/ymcui/Chinese-BERT-wwm
- Chinese MacBERT: https://github.com/ymcui/MacBERT
- Chinese ELECTRA: https://github.com/ymcui/Chinese-ELECTRA
- Chinese XLNet: https://github.com/ymcui/Chinese-XLNet
- Knowledge Distillation Toolkit - TextBrewer: https://github.com/airaria/TextBrewer
More resources by HFL: https://github.com/ymcui/HFL-Anthology
## Citation
If you find the technical report or resource is useful, please cite the following technical report in your paper.
- Primary: https://arxiv.org/abs/2004.13922
```
@inproceedings{cui-etal-2020-revisiting,
title = "Revisiting Pre-Trained Models for {C}hinese Natural Language Processing",
author = "Cui, Yiming and
Che, Wanxiang and
Liu, Ting and
Qin, Bing and
Wang, Shijin and
Hu, Guoping",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.findings-emnlp.58",
pages = "657--668",
}
```
- Secondary: https://arxiv.org/abs/1906.08101
```
@article{chinese-bert-wwm,
title={Pre-Training with Whole Word Masking for Chinese BERT},
author={Cui, Yiming and Che, Wanxiang and Liu, Ting and Qin, Bing and Yang, Ziqing and Wang, Shijin and Hu, Guoping},
journal={arXiv preprint arXiv:1906.08101},
year={2019}
}
```

37
bert/deberta-v2-large-japanese-char-wwm-onnx/config.json Normal file
View File

@@ -0,0 +1,37 @@
{
"architectures": [
"DebertaV2ForMaskedLM"
],
"attention_head_size": 64,
"attention_probs_dropout_prob": 0.1,
"conv_act": "gelu",
"conv_kernel_size": 3,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-07,
"max_position_embeddings": 512,
"max_relative_positions": -1,
"model_type": "deberta-v2",
"norm_rel_ebd": "layer_norm",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 0,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"pooler_hidden_size": 1024,
"pos_att_type": [
"p2c",
"c2p"
],
"position_biased_input": false,
"position_buckets": 256,
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float16",
"transformers_version": "4.25.1",
"type_vocab_size": 0,
"vocab_size": 22012
}

7
bert/deberta-v2-large-japanese-char-wwm-onnx/special_tokens_map.json Normal file
View File

@@ -0,0 +1,7 @@
{
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"unk_token": "[UNK]"
}

22116
bert/deberta-v2-large-japanese-char-wwm-onnx/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

19
bert/deberta-v2-large-japanese-char-wwm-onnx/tokenizer_config.json Normal file
View File

@@ -0,0 +1,19 @@
{
"cls_token": "[CLS]",
"do_lower_case": false,
"do_subword_tokenize": true,
"do_word_tokenize": true,
"jumanpp_kwargs": null,
"mask_token": "[MASK]",
"mecab_kwargs": null,
"model_max_length": 1000000000000000019884624838656,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"subword_tokenizer_type": "character",
"sudachi_kwargs": null,
"tokenizer_class": "BertJapaneseTokenizer",
"unk_token": "[UNK]",
"word_tokenizer_type": "basic"
}

22012
bert/deberta-v2-large-japanese-char-wwm-onnx/vocab.txt Normal file
View File

File diff suppressed because it is too large Load Diff

34
bert/deberta-v2-large-japanese-char-wwm/.gitattributes vendored
View File

@@ -1,34 +0,0 @@
*.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

89
bert/deberta-v2-large-japanese-char-wwm/README.md
View File

@@ -1,89 +0,0 @@
---
language: ja
license: cc-by-sa-4.0
library_name: transformers
tags:
- deberta
- deberta-v2
- fill-mask
- character
- wwm
datasets:
- wikipedia
- cc100
- oscar
metrics:
- accuracy
mask_token: "[MASK]"
widget:
- text: "京都大学で自然言語処理を[MASK][MASK]する。"
---
# Model Card for Japanese character-level DeBERTa V2 large
## Model description
This is a Japanese DeBERTa V2 large model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR.
This model is trained with character-level tokenization and whole word masking.
## How to use
You can use this model for masked language modeling as follows:
```python
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained('ku-nlp/deberta-v2-large-japanese-char-wwm')
model = AutoModelForMaskedLM.from_pretrained('ku-nlp/deberta-v2-large-japanese-char-wwm')
sentence = '京都大学で自然言語処理を[MASK][MASK]する。'
encoding = tokenizer(sentence, return_tensors='pt')
...
```
You can also fine-tune this model on downstream tasks.
## Tokenization
There is no need to tokenize texts in advance, and you can give raw texts to the tokenizer.
The texts are tokenized into character-level tokens by [sentencepiece](https://github.com/google/sentencepiece).
## Training data
We used the following corpora for pre-training:
- Japanese Wikipedia (as of 20221020, 3.2GB, 27M sentences, 1.3M documents)
- Japanese portion of CC-100 (85GB, 619M sentences, 66M documents)
- Japanese portion of OSCAR (54GB, 326M sentences, 25M documents)
Note that we filtered out documents annotated with "header", "footer", or "noisy" tags in OSCAR.
Also note that Japanese Wikipedia was duplicated 10 times to make the total size of the corpus comparable to that of CC-100 and OSCAR. As a result, the total size of the training data is 171GB.
## Training procedure
We first segmented texts in the corpora into words using [Juman++ 2.0.0-rc3](https://github.com/ku-nlp/jumanpp/releases/tag/v2.0.0-rc3) for whole word masking.
Then, we built a sentencepiece model with 22,012 tokens including all characters that appear in the training corpus.
We tokenized raw corpora into character-level subwords using the sentencepiece model and trained the Japanese DeBERTa model using [transformers](https://github.com/huggingface/transformers) library.
The training took 26 days using 16 NVIDIA A100-SXM4-40GB GPUs.
The following hyperparameters were used during pre-training:
- learning_rate: 1e-4
- per_device_train_batch_size: 26
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 8
- total_train_batch_size: 3,328
- max_seq_length: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear schedule with warmup (lr = 0 at 300k steps)
- training_steps: 260,000
- warmup_steps: 10,000
The accuracy of the trained model on the masked language modeling task was 0.795.
The evaluation set consists of 5,000 randomly sampled documents from each of the training corpora.
## Acknowledgments
This work was supported by Joint Usage/Research Center for Interdisciplinary Large-scale Information Infrastructures (JHPCN) through General Collaboration Project no. jh221004, "Developing a Platform for Constructing and Sharing of Large-Scale Japanese Language Models".
For training models, we used the mdx: a platform for the data-driven future.

27
bert/deberta-v3-large/.gitattributes vendored
View File

@@ -1,27 +0,0 @@
*.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

93
bert/deberta-v3-large/README.md
View File

@@ -1,93 +0,0 @@
---
language: en
tags:
- deberta
- deberta-v3
- fill-mask
thumbnail: https://huggingface.co/front/thumbnails/microsoft.png
license: mit
---
## DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
[DeBERTa](https://arxiv.org/abs/2006.03654) improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data.
In [DeBERTa V3](https://arxiv.org/abs/2111.09543), we further improved the efficiency of DeBERTa using ELECTRA-Style pre-training with Gradient Disentangled Embedding Sharing. Compared to DeBERTa, our V3 version significantly improves the model performance on downstream tasks. You can find more technique details about the new model from our [paper](https://arxiv.org/abs/2111.09543).
Please check the [official repository](https://github.com/microsoft/DeBERTa) for more implementation details and updates.
The DeBERTa V3 large model comes with 24 layers and a hidden size of 1024. It has 304M backbone parameters with a vocabulary containing 128K tokens which introduces 131M parameters in the Embedding layer. This model was trained using the 160GB data as DeBERTa V2.
#### Fine-tuning on NLU tasks
We present the dev results on SQuAD 2.0 and MNLI tasks.
| Model |Vocabulary(K)|Backbone #Params(M)| SQuAD 2.0(F1/EM) | MNLI-m/mm(ACC)|
|-------------------|----------|-------------------|-----------|----------|
| RoBERTa-large |50 |304 | 89.4/86.5 | 90.2 |
| XLNet-large |32 |- | 90.6/87.9 | 90.8 |
| DeBERTa-large |50 |- | 90.7/88.0 | 91.3 |
| **DeBERTa-v3-large**|128|304 | **91.5/89.0**| **91.8/91.9**|
#### Fine-tuning with HF transformers
```bash
#!/bin/bash
cd transformers/examples/pytorch/text-classification/
pip install datasets
export TASK_NAME=mnli
output_dir="ds_results"
num_gpus=8
batch_size=8
python -m torch.distributed.launch --nproc_per_node=${num_gpus} \
run_glue.py \
--model_name_or_path microsoft/deberta-v3-large \
--task_name $TASK_NAME \
--do_train \
--do_eval \
--evaluation_strategy steps \
--max_seq_length 256 \
--warmup_steps 50 \
--per_device_train_batch_size ${batch_size} \
--learning_rate 6e-6 \
--num_train_epochs 2 \
--output_dir $output_dir \
--overwrite_output_dir \
--logging_steps 1000 \
--logging_dir $output_dir
```
### Citation
If you find DeBERTa useful for your work, please cite the following papers:
``` latex
@misc{he2021debertav3,
title={DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing},
author={Pengcheng He and Jianfeng Gao and Weizhu Chen},
year={2021},
eprint={2111.09543},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
``` latex
@inproceedings{
he2021deberta,
title={DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION},
author={Pengcheng He and Xiaodong Liu and Jianfeng Gao and Weizhu Chen},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=XPZIaotutsD}
}
```