From 16af9ff7b0a22abfaff24de3ae00e695d7c25dd9 Mon Sep 17 00:00:00 2001 From: timoeller Date: Fri, 14 Jun 2019 17:42:46 +0200 Subject: [PATCH] Add German Bert model to code, update readme --- README.md | 1 + pytorch_pretrained_bert/modeling.py | 1 + pytorch_pretrained_bert/tokenization.py | 2 ++ 3 files changed, 4 insertions(+) diff --git a/README.md b/README.md index b1cb84619d..1d734f9df9 100644 --- a/README.md +++ b/README.md @@ -491,6 +491,7 @@ where - `bert-base-multilingual-uncased`: (Orig, not recommended) 102 languages, 12-layer, 768-hidden, 12-heads, 110M parameters - `bert-base-multilingual-cased`: **(New, recommended)** 104 languages, 12-layer, 768-hidden, 12-heads, 110M parameters - `bert-base-chinese`: Chinese Simplified and Traditional, 12-layer, 768-hidden, 12-heads, 110M parameters + - `bert-base-german-cased`: Trained on German data only, 12-layer, 768-hidden, 12-heads, 110M parameters [Performance Evaluation](https://deepset.ai/german-bert) - `openai-gpt`: OpenAI English model, 12-layer, 768-hidden, 12-heads, 110M parameters - `transfo-xl-wt103`: Transformer-XL English model trained on wikitext-103, 18-layer, 1024-hidden, 16-heads, 257M parameters - `gpt2`: OpenAI GPT-2 English model, 12-layer, 768-hidden, 12-heads, 117M parameters diff --git a/pytorch_pretrained_bert/modeling.py b/pytorch_pretrained_bert/modeling.py index bbf8f4800b..3006d8e971 100644 --- a/pytorch_pretrained_bert/modeling.py +++ b/pytorch_pretrained_bert/modeling.py @@ -44,6 +44,7 @@ PRETRAINED_MODEL_ARCHIVE_MAP = { 'bert-base-multilingual-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased.tar.gz", 'bert-base-multilingual-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased.tar.gz", 'bert-base-chinese': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese.tar.gz", + 'bert-base-german-cased': "https://int-deepset-models-bert.s3.eu-central-1.amazonaws.com/pytorch/bert-base-german-cased.tar.gz", } BERT_CONFIG_NAME = 'bert_config.json' TF_WEIGHTS_NAME = 'model.ckpt' diff --git a/pytorch_pretrained_bert/tokenization.py b/pytorch_pretrained_bert/tokenization.py index 3937d6e011..26c172dc69 100644 --- a/pytorch_pretrained_bert/tokenization.py +++ b/pytorch_pretrained_bert/tokenization.py @@ -34,6 +34,7 @@ PRETRAINED_VOCAB_ARCHIVE_MAP = { 'bert-base-multilingual-uncased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-vocab.txt", 'bert-base-multilingual-cased': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-vocab.txt", 'bert-base-chinese': "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-vocab.txt", + 'bert-base-german-cased': "https://int-deepset-models-bert.s3.eu-central-1.amazonaws.com/pytorch/bert-base-german-cased-vocab.txt", } PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP = { 'bert-base-uncased': 512, @@ -43,6 +44,7 @@ PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP = { 'bert-base-multilingual-uncased': 512, 'bert-base-multilingual-cased': 512, 'bert-base-chinese': 512, + 'bert-base-german-cased': 512, } VOCAB_NAME = 'vocab.txt'