For CPU users:

pip install transformers==4.40.2 huggingface-hub==0.20.3 torch==2.2.1

For GPU (CUDA) users:

pip install transformers==4.40.2 huggingface-hub==0.20.3pip install torch==2.2.1 --index-url https://download.pytorch.org/whl/cu121

• According to the May 2024 releases, “transformers” ≥ 4.41 depends on“huggingface-hub” ≥ 0.23. The “transformers” (4.40.2) and“huggingface-hub” (0.20.3) can display progress bars when downloadingBERT models.
• Proxy users may use the “global mode” (全局模式) to downloadmodels.
• If you find the errorHTTPSConnectionPool(host='huggingface.co', port=443),please try to (1) reinstallAnaconda so thatsome unknown issues may be fixed, or (2) downgrade the “urllib3” package to version≤ 1.25.11 (pip install urllib3==1.25.11) so that it willuse HTTP proxies (rather than HTTPS proxies as in later versions) toconnect to Hugging Face.

Guidance for FMAT

Step 1: Download BERT Models

Useset_cache_folder() to change the default HuggingFacecache directory from “%USERPROFILE%/.cache/huggingface/hub” to anotherfolder you like, so that all models would be downloaded and saved inthat folder. Keep in mind: This function takes effect only for thecurrent R sessiontemporarily, so you should run this each timeBEFORE you use other FMAT functions in an R session.

UseBERT_download() to downloadBERT models. A full list of BERT models areavailable atHuggingFace.

UseBERT_info() andBERT_vocab() to obtaindetailed information of BERT models.

Step 2: Design FMAT Queries

Design queries that conceptually represent the constructs you wouldmeasure (seeBao, 2024,JPSP for how to design queries).

UseFMAT_query() and/orFMAT_query_bind()to prepare adata.table of queries.

Step 3: Run FMAT

UseFMAT_run() to get raw data (probability estimates)for further analysis.

Several steps of preprocessing have been included in the function foreasier use (seeFMAT_run() for details).

• For BERT variants using<mask> rather than[MASK] as the mask token, the input query will beautomatically modified so that users can always use[MASK] in query design.
• For some BERT variants, special prefix characters such as\u0120 and\u2581 will beautomatically added to match the whole words (rather thansubwords) for[MASK].

Notes

• Improvements are ongoing, especially for more diverse (less popular)BERT models.
• If you have problems using the functions, please report atGitHub Issues.

Guidance for GPUAcceleration

By default, theFMAT package uses CPU to enable thefunctionality for all users. But for advanced users who want toaccelerate the pipeline with GPU, theFMAT_run() functionsupports using a GPU device.

Test results (on the developer’s computer, depending on BERT modelsize):

• CPU (Intel 13th-Gen i7-1355U): 500~1000 queries/min
• GPU (NVIDIA GeForce RTX 2050): 1500~3000 queries/min

Checklist:

1. Ensure that you have an NVIDIA GPU device (e.g., GeForce RTX Series)and an NVIDIA GPU driver installed on your system.
2. Install PyTorch (Pythontorch package) with CUDAsupport.
   • Find guidance for installation command athttps://pytorch.org/get-started/locally/.
   • CUDA is available only on Windows and Linux, but not on MacOS.
   • If you have installed a version oftorch without CUDAsupport, please first uninstall it (command:pip uninstall torch).
   • You may also install the corresponding version of CUDA Toolkit(e.g., for thetorch version supporting CUDA 12.1, the sameversion ofCUDAToolkit 12.1 may also be installed).

BERT Models

Classic 12 English Models

The reliability and validity of the following 12 English BERT modelsfor the FMAT have been established in our earlier research.

(model name on Hugging Face - model file size)

1. bert-base-uncased(420 MB)
2. bert-base-cased(416 MB)
3. bert-large-uncased(1283 MB)
4. bert-large-cased(1277 MB)
5. distilbert-base-uncased(256 MB)
6. distilbert-base-cased(251 MB)
7. albert-base-v1(45 MB)
8. albert-base-v2(45 MB)
9. roberta-base (476MB)
10. distilroberta-base(316 MB)
11. vinai/bertweet-base(517 MB)
12. vinai/bertweet-large(1356 MB)

For details aboutBERT, see:

• What is Fill-Mask?[HuggingFace]
• AnExplorable BERT [HuggingFace]
• BERTModel Documentation [HuggingFace]
• IllustratedBERT
• VisualGuide to BERT

library(FMAT)models=c("bert-base-uncased","bert-base-cased","bert-large-uncased","bert-large-cased","distilbert-base-uncased","distilbert-base-cased","albert-base-v1","albert-base-v2","roberta-base","distilroberta-base","vinai/bertweet-base","vinai/bertweet-large")BERT_download(models)

ℹ Device Info:R Packages:FMAT          2024.5reticulate    1.36.1Python Packages:transformers  4.40.2torch         2.2.1+cu121NVIDIA GPU CUDA Support:CUDA Enabled: TRUECUDA Version: 12.1GPU (Device): NVIDIA GeForce RTX 2050── Downloading model "bert-base-uncased" ──────────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 570/570 [00:00<00:00, 114kB/s]→ (2) Downloading tokenizer...tokenizer_config.json: 100%|██████████| 48.0/48.0 [00:00<00:00, 23.9kB/s]vocab.txt: 100%|██████████| 232k/232k [00:00<00:00, 1.50MB/s]tokenizer.json: 100%|██████████| 466k/466k [00:00<00:00, 1.98MB/s]→ (3) Downloading model...model.safetensors: 100%|██████████| 440M/440M [00:36<00:00, 12.1MB/s] ✔ Successfully downloaded model "bert-base-uncased"── Downloading model "bert-base-cased" ────────────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 570/570 [00:00<00:00, 63.3kB/s]→ (2) Downloading tokenizer...tokenizer_config.json: 100%|██████████| 49.0/49.0 [00:00<00:00, 8.66kB/s]vocab.txt: 100%|██████████| 213k/213k [00:00<00:00, 1.39MB/s]tokenizer.json: 100%|██████████| 436k/436k [00:00<00:00, 10.1MB/s]→ (3) Downloading model...model.safetensors: 100%|██████████| 436M/436M [00:37<00:00, 11.6MB/s] ✔ Successfully downloaded model "bert-base-cased"── Downloading model "bert-large-uncased" ─────────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 571/571 [00:00<00:00, 268kB/s]→ (2) Downloading tokenizer...tokenizer_config.json: 100%|██████████| 48.0/48.0 [00:00<00:00, 12.0kB/s]vocab.txt: 100%|██████████| 232k/232k [00:00<00:00, 1.50MB/s]tokenizer.json: 100%|██████████| 466k/466k [00:00<00:00, 1.99MB/s]→ (3) Downloading model...model.safetensors: 100%|██████████| 1.34G/1.34G [01:36<00:00, 14.0MB/s]✔ Successfully downloaded model "bert-large-uncased"── Downloading model "bert-large-cased" ───────────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 762/762 [00:00<00:00, 125kB/s]→ (2) Downloading tokenizer...tokenizer_config.json: 100%|██████████| 49.0/49.0 [00:00<00:00, 12.3kB/s]vocab.txt: 100%|██████████| 213k/213k [00:00<00:00, 1.41MB/s]tokenizer.json: 100%|██████████| 436k/436k [00:00<00:00, 5.39MB/s]→ (3) Downloading model...model.safetensors: 100%|██████████| 1.34G/1.34G [01:35<00:00, 14.0MB/s]✔ Successfully downloaded model "bert-large-cased"── Downloading model "distilbert-base-uncased" ────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 483/483 [00:00<00:00, 161kB/s]→ (2) Downloading tokenizer...tokenizer_config.json: 100%|██████████| 48.0/48.0 [00:00<00:00, 9.46kB/s]vocab.txt: 100%|██████████| 232k/232k [00:00<00:00, 16.5MB/s]tokenizer.json: 100%|██████████| 466k/466k [00:00<00:00, 14.8MB/s]→ (3) Downloading model...model.safetensors: 100%|██████████| 268M/268M [00:19<00:00, 13.5MB/s] ✔ Successfully downloaded model "distilbert-base-uncased"── Downloading model "distilbert-base-cased" ──────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 465/465 [00:00<00:00, 233kB/s]→ (2) Downloading tokenizer...tokenizer_config.json: 100%|██████████| 49.0/49.0 [00:00<00:00, 9.80kB/s]vocab.txt: 100%|██████████| 213k/213k [00:00<00:00, 1.39MB/s]tokenizer.json: 100%|██████████| 436k/436k [00:00<00:00, 8.70MB/s]→ (3) Downloading model...model.safetensors: 100%|██████████| 263M/263M [00:24<00:00, 10.9MB/s] ✔ Successfully downloaded model "distilbert-base-cased"── Downloading model "albert-base-v1" ─────────────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 684/684 [00:00<00:00, 137kB/s]→ (2) Downloading tokenizer...tokenizer_config.json: 100%|██████████| 25.0/25.0 [00:00<00:00, 3.57kB/s]spiece.model: 100%|██████████| 760k/760k [00:00<00:00, 4.93MB/s]tokenizer.json: 100%|██████████| 1.31M/1.31M [00:00<00:00, 13.4MB/s]→ (3) Downloading model...model.safetensors: 100%|██████████| 47.4M/47.4M [00:03<00:00, 13.4MB/s]✔ Successfully downloaded model "albert-base-v1"── Downloading model "albert-base-v2" ─────────────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 684/684 [00:00<00:00, 137kB/s]→ (2) Downloading tokenizer...tokenizer_config.json: 100%|██████████| 25.0/25.0 [00:00<00:00, 4.17kB/s]spiece.model: 100%|██████████| 760k/760k [00:00<00:00, 5.10MB/s]tokenizer.json: 100%|██████████| 1.31M/1.31M [00:00<00:00, 6.93MB/s]→ (3) Downloading model...model.safetensors: 100%|██████████| 47.4M/47.4M [00:03<00:00, 13.8MB/s]✔ Successfully downloaded model "albert-base-v2"── Downloading model "roberta-base" ───────────────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 481/481 [00:00<00:00, 80.3kB/s]→ (2) Downloading tokenizer...tokenizer_config.json: 100%|██████████| 25.0/25.0 [00:00<00:00, 6.25kB/s]vocab.json: 100%|██████████| 899k/899k [00:00<00:00, 2.72MB/s]merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 8.22MB/s]tokenizer.json: 100%|██████████| 1.36M/1.36M [00:00<00:00, 8.56MB/s]→ (3) Downloading model...model.safetensors: 100%|██████████| 499M/499M [00:38<00:00, 12.9MB/s] ✔ Successfully downloaded model "roberta-base"── Downloading model "distilroberta-base" ─────────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 480/480 [00:00<00:00, 96.4kB/s]→ (2) Downloading tokenizer...tokenizer_config.json: 100%|██████████| 25.0/25.0 [00:00<00:00, 12.0kB/s]vocab.json: 100%|██████████| 899k/899k [00:00<00:00, 6.59MB/s]merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 9.46MB/s]tokenizer.json: 100%|██████████| 1.36M/1.36M [00:00<00:00, 11.5MB/s]→ (3) Downloading model...model.safetensors: 100%|██████████| 331M/331M [00:25<00:00, 13.0MB/s] ✔ Successfully downloaded model "distilroberta-base"── Downloading model "vinai/bertweet-base" ────────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 558/558 [00:00<00:00, 187kB/s]→ (2) Downloading tokenizer...vocab.txt: 100%|██████████| 843k/843k [00:00<00:00, 7.44MB/s]bpe.codes: 100%|██████████| 1.08M/1.08M [00:00<00:00, 7.01MB/s]tokenizer.json: 100%|██████████| 2.91M/2.91M [00:00<00:00, 9.10MB/s]→ (3) Downloading model...pytorch_model.bin: 100%|██████████| 543M/543M [00:48<00:00, 11.1MB/s] ✔ Successfully downloaded model "vinai/bertweet-base"── Downloading model "vinai/bertweet-large" ───────────────────────────────────────→ (1) Downloading configuration...config.json: 100%|██████████| 614/614 [00:00<00:00, 120kB/s]→ (2) Downloading tokenizer...vocab.json: 100%|██████████| 899k/899k [00:00<00:00, 5.90MB/s]merges.txt: 100%|██████████| 456k/456k [00:00<00:00, 7.30MB/s]tokenizer.json: 100%|██████████| 1.36M/1.36M [00:00<00:00, 8.31MB/s]→ (3) Downloading model...pytorch_model.bin: 100%|██████████| 1.42G/1.42G [02:29<00:00, 9.53MB/s]✔ Successfully downloaded model "vinai/bertweet-large"── Downloaded models: ──                           sizealbert-base-v1            45 MBalbert-base-v2            45 MBbert-base-cased          416 MBbert-base-uncased        420 MBbert-large-cased        1277 MBbert-large-uncased      1283 MBdistilbert-base-cased    251 MBdistilbert-base-uncased  256 MBdistilroberta-base       316 MBroberta-base             476 MBvinai/bertweet-base      517 MBvinai/bertweet-large    1356 MB✔ Downloaded models saved at C:/Users/Bruce/.cache/huggingface/hub (6.52 GB)

BERT_info(models)

                      model   size vocab  dims   mask                     <fctr> <char> <int> <int> <char> 1:       bert-base-uncased  420MB 30522   768 [MASK] 2:         bert-base-cased  416MB 28996   768 [MASK] 3:      bert-large-uncased 1283MB 30522  1024 [MASK] 4:        bert-large-cased 1277MB 28996  1024 [MASK] 5: distilbert-base-uncased  256MB 30522   768 [MASK] 6:   distilbert-base-cased  251MB 28996   768 [MASK] 7:          albert-base-v1   45MB 30000   128 [MASK] 8:          albert-base-v2   45MB 30000   128 [MASK] 9:            roberta-base  476MB 50265   768 <mask>10:      distilroberta-base  316MB 50265   768 <mask>11:     vinai/bertweet-base  517MB 64001   768 <mask>12:    vinai/bertweet-large 1356MB 50265  1024 <mask>

(Tested 2024-05-16 on the developer’s computer: HP Probook 450 G10Notebook PC)

General 30 English and30 Chinese Models

We are using a more comprehensive list of 30 English BERT models and30 Chinese BERT models in our ongoing and future projects.

library(FMAT)set_cache_folder("G:/HuggingFace_Cache/")# models saved in my portable SSD## 30 English Modelsmodels.en=c(# BERT (base/large/large-wwm, uncased/cased)"bert-base-uncased","bert-base-cased","bert-large-uncased","bert-large-cased","bert-large-uncased-whole-word-masking","bert-large-cased-whole-word-masking",# ALBERT (base/large/xlarge, v1/v2)"albert-base-v1","albert-base-v2","albert-large-v1","albert-large-v2","albert-xlarge-v1","albert-xlarge-v2",# DistilBERT (uncased/cased/distilroberta)"distilbert-base-uncased","distilbert-base-cased","distilroberta-base",# RoBERTa (roberta/muppet, base/large)"roberta-base","roberta-large","facebook/muppet-roberta-base","facebook/muppet-roberta-large",# ELECTRA (base/large)"google/electra-base-generator","google/electra-large-generator",# MobileBERT (uncased)"google/mobilebert-uncased",# ModernBERT (base/large)"answerdotai/ModernBERT-base",# transformers >= 4.48.0"answerdotai/ModernBERT-large",# transformers >= 4.48.0# [Tweets] (BERT/RoBERTa/BERTweet-base/BERTweet-large)"muhtasham/base-mlm-tweet","cardiffnlp/twitter-roberta-base","vinai/bertweet-base","vinai/bertweet-large",# [PubMed Abstracts] (BiomedBERT, base/large)"microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract","microsoft/BiomedNLP-BiomedBERT-large-uncased-abstract")## 30 Chinese Modelsmodels.cn=c(# BERT [Google]"bert-base-chinese",# BERT [Alibaba-PAI] (base/ck-base/ck-large/ck-huge)"alibaba-pai/pai-bert-base-zh","alibaba-pai/pai-ckbert-base-zh","alibaba-pai/pai-ckbert-large-zh","alibaba-pai/pai-ckbert-huge-zh",# BERT [HFL] (wwm, bert-wiki/bert-ext/roberta-ext)"hfl/chinese-bert-wwm","hfl/chinese-bert-wwm-ext","hfl/chinese-roberta-wwm-ext",# BERT [HFL] (lert/macbert/electra, base/large)"hfl/chinese-lert-base","hfl/chinese-lert-large","hfl/chinese-macbert-base","hfl/chinese-macbert-large","hfl/chinese-electra-180g-base-generator","hfl/chinese-electra-180g-large-generator",# RoBERTa [UER] (H=512/768, L=6/8/10/12)"uer/chinese_roberta_L-6_H-512","uer/chinese_roberta_L-8_H-512","uer/chinese_roberta_L-10_H-512","uer/chinese_roberta_L-12_H-512","uer/chinese_roberta_L-6_H-768","uer/chinese_roberta_L-8_H-768","uer/chinese_roberta_L-10_H-768","uer/chinese_roberta_L-12_H-768",# RoBERTa [UER] (wwm, base/large)"uer/roberta-base-wwm-chinese-cluecorpussmall","uer/roberta-large-wwm-chinese-cluecorpussmall",# BERT [IDEA-CCNL] (MacBERT/TCBert-base/TCBert-large)"IDEA-CCNL/Erlangshen-MacBERT-325M-NLI-Chinese","IDEA-CCNL/Erlangshen-TCBert-330M-Classification-Chinese","IDEA-CCNL/Erlangshen-TCBert-330M-Sentence-Embedding-Chinese",# RoBERTa [IDEA-CCNL] (UniMC, base/large)"IDEA-CCNL/Erlangshen-UniMC-RoBERTa-110M-Chinese","IDEA-CCNL/Erlangshen-UniMC-RoBERTa-330M-Chinese",# MegatronBERT [IDEA-CCNL] (huge)"IDEA-CCNL/Erlangshen-UniMC-MegatronBERT-1.3B-Chinese")BERT_info(models.en)BERT_info(models.cn)

Information of the 30English Models

                                                    model       type     param vocab embed layer heads   mask                                                   <fctr>     <fctr>     <int> <int> <int> <int> <int> <fctr> 1:                                     bert-base-uncased       bert 109482240 30522   768    12    12 [MASK] 2:                                       bert-base-cased       bert 108310272 28996   768    12    12 [MASK] 3:                                    bert-large-uncased       bert 335141888 30522  1024    24    16 [MASK] 4:                                      bert-large-cased       bert 333579264 28996  1024    24    16 [MASK] 5:                 bert-large-uncased-whole-word-masking       bert 335141888 30522  1024    24    16 [MASK] 6:                   bert-large-cased-whole-word-masking       bert 333579264 28996  1024    24    16 [MASK] 7:                                        albert-base-v1     albert  11683584 30000   128    12    12 [MASK] 8:                                        albert-base-v2     albert  11683584 30000   128    12    12 [MASK] 9:                                       albert-large-v1     albert  17683968 30000   128    24    16 [MASK]10:                                       albert-large-v2     albert  17683968 30000   128    24    16 [MASK]11:                                      albert-xlarge-v1     albert  58724864 30000   128    24    16 [MASK]12:                                      albert-xlarge-v2     albert  58724864 30000   128    24    16 [MASK]13:                               distilbert-base-uncased distilbert  66362880 30522   768     6    12 [MASK]14:                                 distilbert-base-cased distilbert  65190912 28996   768     6    12 [MASK]15:                                    distilroberta-base    roberta  82118400 50265   768     6    12 <mask>16:                                          roberta-base    roberta 124645632 50265   768    12    12 <mask>17:                                         roberta-large    roberta 355359744 50265  1024    24    16 <mask>18:                          facebook/muppet-roberta-base    roberta 124645632 50265   768    12    12 <mask>19:                         facebook/muppet-roberta-large    roberta 355359744 50265  1024    24    16 <mask>20:                         google/electra-base-generator    electra  33511168 30522   768    12     4 [MASK]21:                        google/electra-large-generator    electra  50999552 30522  1024    24     4 [MASK]22:                             google/mobilebert-uncased mobilebert  24581888 30522   128    24     4 [MASK]23:                           answerdotai/ModernBERT-base modernbert 149014272 50368   768    22    12 [MASK]24:                          answerdotai/ModernBERT-large modernbert 394781696 50368  1024    28    16 [MASK]25:                              muhtasham/base-mlm-tweet       bert 109482240 30522   768    12    12 [MASK]26:                       cardiffnlp/twitter-roberta-base    roberta 124645632 50265   768    12    12 <mask>27:                                   vinai/bertweet-base    roberta 134899968 64001   768    12    12 <mask>28:                                  vinai/bertweet-large    roberta 355359744 50265  1024    24    16 <mask>29:  microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract       bert 109482240 30522   768    12    12 [MASK]30: microsoft/BiomedNLP-BiomedBERT-large-uncased-abstract       bert 335141888 30522  1024    24    16 [MASK]                                                    model       type     param vocab embed layer heads   mask

Missing values of year tokens (1800~2019):

• "albert" series: 3 missing
  • 1807, 1809, 1817
• "ModernBERT" series: 65 missing
  • 1801~1829, 1831~1839, 1841~1847, 1849, 1851~1859, 1869, 1871~1875,1877~1879, 1883
• "roberta" series,"muppet" series,"distilroberta-base","cardiffnlp/twitter-roberta-base","vinai/bertweet-large": 79 missing
  • 1801~1829, 1831~1839, 1841~1849, 1851~1859, 1864, 1866~1869,1871~1879, 1881~1885, 1887, 1891, 1892, 1894
• "vinai/bertweet-base": 29 missing
  • 1801~1811, 1813~1814, 1816~1819, 1821~1823, 1825~1829, 1831, 1833,1834, 1843
• "BiomedBERT" series: 163 missing
  • 1801~1949, 1951~1959, 1961~1964, 1967

Information of the 30Chinese Models

                                                          model          type      param vocab embed layer heads   mask                                                         <fctr>        <fctr>      <int> <int> <int> <int> <int> <fctr> 1:                                           bert-base-chinese          bert  102267648 21128   768    12    12 [MASK] 2:                                alibaba-pai/pai-bert-base-zh          bert  102267648 21128   768    12    12 [MASK] 3:                              alibaba-pai/pai-ckbert-base-zh          bert  102269184 21130   768    12    12 [MASK] 4:                             alibaba-pai/pai-ckbert-large-zh          bert  325524480 21130  1024    24    16 [MASK] 5:                              alibaba-pai/pai-ckbert-huge-zh megatron-bert 1257367552 21248  2048    24     8 [MASK] 6:                                        hfl/chinese-bert-wwm          bert  102267648 21128   768    12    12 [MASK] 7:                                    hfl/chinese-bert-wwm-ext          bert  102267648 21128   768    12    12 [MASK] 8:                                 hfl/chinese-roberta-wwm-ext          bert  102267648 21128   768    12    12 [MASK] 9:                                       hfl/chinese-lert-base          bert  102267648 21128   768    12    12 [MASK]10:                                      hfl/chinese-lert-large          bert  325522432 21128  1024    24    16 [MASK]11:                                    hfl/chinese-macbert-base          bert  102267648 21128   768    12    12 [MASK]12:                                   hfl/chinese-macbert-large          bert  325522432 21128  1024    24    16 [MASK]13:                     hfl/chinese-electra-180g-base-generator       electra   22108608 21128   768    12     3 [MASK]14:                    hfl/chinese-electra-180g-large-generator       electra   41380096 21128  1024    24     4 [MASK]15:                               uer/chinese_roberta_L-6_H-512          bert   30258688 21128   512     6     8 [MASK]16:                               uer/chinese_roberta_L-8_H-512          bert   36563456 21128   512     8     8 [MASK]17:                              uer/chinese_roberta_L-10_H-512          bert   42868224 21128   512    10     8 [MASK]18:                              uer/chinese_roberta_L-12_H-512          bert   49172992 21128   512    12     8 [MASK]19:                               uer/chinese_roberta_L-6_H-768          bert   59740416 21128   768     6    12 [MASK]20:                               uer/chinese_roberta_L-8_H-768          bert   73916160 21128   768     8    12 [MASK]21:                              uer/chinese_roberta_L-10_H-768          bert   88091904 21128   768    10    12 [MASK]22:                              uer/chinese_roberta_L-12_H-768          bert  102267648 21128   768    12    12 [MASK]23:                uer/roberta-base-wwm-chinese-cluecorpussmall          bert  102267648 21128   768    12    12 [MASK]24:               uer/roberta-large-wwm-chinese-cluecorpussmall          bert  325522432 21128  1024    24    16 [MASK]25:               IDEA-CCNL/Erlangshen-MacBERT-325M-NLI-Chinese          bert  325625856 21229  1024    24    16 [MASK]26:     IDEA-CCNL/Erlangshen-TCBert-330M-Classification-Chinese          bert  325522432 21128  1024    24    16 [MASK]27: IDEA-CCNL/Erlangshen-TCBert-330M-Sentence-Embedding-Chinese          bert  325522432 21128  1024    24    16 [MASK]28:             IDEA-CCNL/Erlangshen-UniMC-RoBERTa-110M-Chinese          bert  102267648 21128   768    12    12 [MASK]29:             IDEA-CCNL/Erlangshen-UniMC-RoBERTa-330M-Chinese          bert  325522432 21128  1024    24    16 [MASK]30:        IDEA-CCNL/Erlangshen-UniMC-MegatronBERT-1.3B-Chinese megatron-bert 1257367552 21248  2048    24     8 [MASK]                                                          model          type      param vocab embed layer heads   mask

Missing values of year tokens (1800~2019):

• All: 77 missing
  • 1801~1839, 1841~1849, 1851~1859, 1861~1866, 1869, 1872~1879, 1881,1883, 1887, 1891, 1892

Device Information

ℹ Device Info:R Packages:FMAT          2025.12reticulate    1.44.1Python Packages:transformers  4.57.3torch         2.9.1+cu130huggingface-hub  0.36.0NVIDIA GPU CUDA Support:CUDA Enabled: TRUEGPU (Device): NVIDIA GeForce RTX 5060 Laptop GPU

(Tested 2025-12-14 on the developer’s computer: HP Zbook X ZHAN99 G1i16 inch - Intel Ultra9 285H - 64GB/2T - NVIDIA GeForce RTX 5060 LaptopGPU - Mobile Workstation PC)

Related Packages

While the FMAT is an innovative method for thecomputationalintelligent analysis of psychology and society, you may also seekfor an integrative toolbox for other text-analytic methods. Another Rpackage I developed—PsychWordVec—isuseful and user-friendly for word embedding analysis (e.g., the WordEmbedding Association Test, WEAT). Please refer to its documentation andfeel free to use it.