-
## 집현전 중급반 스터디
- 2022년 6월 26일 일요일 9시
- 장동건님 김제우님 김종은님 이기성님 발표
- 논문 링크: https://arxiv.org/abs/1910.01108
> ### Abstract
> As Transfer Learning from large-scale pre-trained models becomes more pr…
-
Any idea what would cause this? It seems like it gets through most of the examples before failing.
```
INFO:transformers.tokenization_utils:loading file https://s3.amazonaws.com/models.huggingface…
-
# 🚀 Add missing tokenizer test files
Several tokenizers currently have no associated tests. I think that adding the test file for one of these tokenizers could be a very good way to make a first cont…
-
I have a notebook (and data) that trains a multilabel roberta model successfully with fast-bert 1.7.0.
I have a new machine and set up the conda env with the latest fast-bert (1.9.1) and the noteb…
laurb updated
3 years ago
-
Another weird error once I was running in colab:
in ()
----> 1 from fast_bert.data_cls import BertDataBunch
2 from fast_bert.learner_cls import BertLearner
3 from fast_bert.metrics …
-
I was wondering if fast Bert support or would in future support pandas data frame as train, test, validation input rather than just CSV files for the same purpose?
-
https://blog.rasa.com/compressing-bert-for-faster-prediction-2/ and https://blog.rasa.com/how-to-benchmark-bert/ they were talking about refereing to rasa-demo sara bot, however the config file config…
-
## 9월 3일 회의 주요 내용
**GPT-3**: BERT 언어모델 보다 성능이 높은 OpenAI에서 제안한 언어모델
**본 과제에서는 BERT를 활용해서 가짜 뉴스 검출 시스템을 확인**
* 윤진
- colab에서 BERT 사용 예제 검토
- BERT 시스템에서 단어 간 유사성을 가시화(visualization) 하는 것을…
-
Hi,
When I load the the tokenizer of `paraphrase-multilingual-MiniLM-L12-v2` model via the hugging face model hub:
```
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/paraphrase-…
-
I'm using this code to get the embeddings of sentences that are in my dataset(I'm using my pretrained model).
`python extract_features.py \
--input_file=/tmp/input.txt \
--output_file=/tmp/ou…