-
BERT is pre-trained using Wikipedia and other sources of normal text, but my problem domain has a very specific vocabulary & grammar. Is there an easy way to train BERT completely from domain specific…
-
If a Text Classification pipeline has [token type IDs](https://huggingface.co/docs/transformers/glossary#token-type-ids), the current `BasePipeline.Preprocess` will fail since there is no `WithReturnT…
-
## Environment info
- `transformers` version: 4.6.0
- Platform: Windows-10-10.0.19041-SP0
- Python version: 3.8.3
- PyTorch version (GPU?): 1.7.1 (True)
- Using GPU in script?: Possibly?
- Usi…
-
Could you process the following report?
[0001041588-20-000001.txt](https://github.com/yuxuanbrandeis/Julex/files/12090657/0001041588-20-000001.txt)
-
Hi,
I ran the script and then get the following error. I follow the suggestion to set the environment variable "export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True" at the terminal session, but…
-
I am getting this error while using keybert, and I have no idea on how to resolve it.
IsADirectoryError: [Errno 21] Is a directory: '/data/bdlml/mkabra/nltk_data/corpora/stopwords'
I deleted the …
-
### System Info
- `transformers` version: 4.41.2
- Platform: Linux-5.11.0-41-generic-x86_64-with-glibc2.31
- Python version: 3.11.9
- Huggingface_hub version: 0.23.3
- Safetensors version: 0.4.…
-
Thanks for your research and it is a breakthrough to have a entity level sentiment dataset for financial domain.
After reading the paper, I try to reproduce the results of Table 3 for FinBERT-CRF.
…
-
run on scf with a100s
datasets with compnay name, fixed quarter date, average finbert embedding across sentences
-
- [x] Sentiment analysis: FINBERT
![Count Positive + 1](https://github.com/current12/Stat-222-Project/assets/74280000/a802a384-f6dc-4df2-b1fe-6d79a0cb8efd)
[source](https://deliverypdf.ssr…