Instructions to use Rupak100/Question_Answer_Scoring with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Rupak100/Question_Answer_Scoring with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("abhishek/llama-2-7b-hf-small-shards") model = PeftModel.from_pretrained(base_model, "Rupak100/Question_Answer_Scoring") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- cc321ee92e5853fe2e31f3b44b1431063eaf376727bf0f82cc8dccad811ea4bf
- Size of remote file:
- 33.6 MB
- SHA256:
- a77fdfa3cbd60fdac3400cf72f9e3d43834ea5c5bf773050f51351289e2e0a9d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.