Instructions to use Rupak100/Fine_Tuining_Scoring with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Rupak100/Fine_Tuining_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/Fine_Tuining_Scoring") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- f51d3db3ee218cfef7577068422c310e31e4b7da8686154c78b5dd8e64df3740
- Size of remote file:
- 7.56 GB
- SHA256:
- 74c152cdfb87ee69effc032b06cd1285d334117cb1c9820b8a839787bdc6c4f3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.