Text Classification
PEFT
Safetensors
Turkish
lora
fact-verification
turkish
nli
sequence-classification
Instructions to use angeldust007/tr-factbench-electra-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use angeldust007/tr-factbench-electra-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("dbmdz/electra-base-turkish-cased-discriminator") model = PeftModel.from_pretrained(base_model, "angeldust007/tr-factbench-electra-lora") - Notebooks
- Google Colab
- Kaggle
| { | |
| "id2label": { | |
| "0": "supported", | |
| "1": "partially_supported", | |
| "2": "contradicted", | |
| "3": "unverifiable" | |
| }, | |
| "label2id": { | |
| "supported": 0, | |
| "partially_supported": 1, | |
| "contradicted": 2, | |
| "unverifiable": 3 | |
| }, | |
| "num_labels": 4, | |
| "label_descriptions": { | |
| "supported": "The claim is directly supported by the evidence context.", | |
| "partially_supported": "The claim is partially supported; some aspects align with the context but others do not or cannot be confirmed.", | |
| "contradicted": "The claim is explicitly contradicted by the evidence context.", | |
| "unverifiable": "The claim cannot be verified or refuted based on the supplied context alone." | |
| } | |
| } |