Instructions to use predibase/glue_qnli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use predibase/glue_qnli with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1") model = PeftModel.from_pretrained(base_model, "predibase/glue_qnli") - Notebooks
- Google Colab
- Kaggle
Description: Does the response answer the question?
Original dataset: https://huggingface.co/datasets/glue/viewer/qnli
---
Try querying this adapter for free in Lora Land at https://predibase.com/lora-land!
The adapter_category is Academic Benchmarks and the name is Answer Validation (QNLI)
---
Sample input: You are provided a question and a corresponding response below. If the response properly answers the question, please return 0. Otherwise, please return 1.\n\n### Question: What is the seldom used force unit equal to one thousand newtons?\n\n### Response: The kilogram-force leads to an alternate, but rarely used unit of mass: the metric slug (sometimes mug or hyl) is that mass that accelerates at 1 m·s−2 when subjected to a force of 1 kgf.\n\n### Label:
---
Sample output: 1
---
Try using this adapter yourself!
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mistral-7B-v0.1"
peft_model_id = "predibase/glue_qnli"
model = AutoModelForCausalLM.from_pretrained(model_id)
model.load_adapter(peft_model_id)
- Downloads last month
- 7
Model tree for predibase/glue_qnli
Base model
mistralai/Mistral-7B-v0.1