Instructions to use dangkhoa99/falcon-7b-finetuned-QA-MRC-4-bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dangkhoa99/falcon-7b-finetuned-QA-MRC-4-bit with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("ybelkada/falcon-7b-sharded-bf16") model = PeftModel.from_pretrained(base_model, "dangkhoa99/falcon-7b-finetuned-QA-MRC-4-bit") - Notebooks
- Google Colab
- Kaggle
Commit ·
1db1cc0
1
Parent(s): 3909063
add: output file evaluates the model's performance
Browse files- output_evaluate.txt +0 -0
output_evaluate.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|