Instructions to use nullpointer-ind/Jina-CorporateFin-Finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nullpointer-ind/Jina-CorporateFin-Finetuned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nullpointer-ind/Jina-CorporateFin-Finetuned", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("nullpointer-ind/Jina-CorporateFin-Finetuned", trust_remote_code=True) model = AutoModel.from_pretrained("nullpointer-ind/Jina-CorporateFin-Finetuned", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
fixed mistakes in data and retrained (loss 0.26->0.16) for selection the best column for a given query among all other columns
Verified signature5fd0d80
-
Upload tokenizer
Verified signaturef29d8ee -
added column details to aid in(loss 0.52->0.26) selection the best column for a given query among all other columns
Verified signature602b890
-
Upload tokenizer
Verified signatureb677d19 -
newly trained model which is trained to select the best financial statement column for a given query among all the financial statement columns
Verified signature2d4d4ee
-
Upload tokenizer
Verified signature192de2a -
Upload folder using huggingface_hub
Verified signature54383ef -
initial commit
Verified signature3def9c8