|
--- |
|
library_name: transformers |
|
language: |
|
- en |
|
metrics: |
|
- accuracy: 62.3 % accuracy on the 2-label liar test set. |
|
pipeline_tag: text-classification |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
This model classifies news statements as true or false. |
|
|
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. |
|
|
|
- **Finetuned from model:** https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b. |
|
|
|
## How to Get Started with the Model |
|
|
|
Use the code below to get started with the model. |
|
|
|
```python |
|
from peft import AutoPeftModelForCausalLM |
|
from transformers import AutoTokenizer |
|
|
|
model = AutoPeftModelForCausalLM.from_pretrained("baris-yazici/liar_stabilityai_stablelm-2-zephyr-1_6b_PROMPT_TUNING_CAUSAL_LM").to("cuda") |
|
tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-zephyr-1_6b") |
|
|
|
``` |
|
|
|
## Training Details |
|
|
|
### Training Data |
|
The liar dataset can be accessed from: https://huggingface.co/datasets/liar. |
|
|
|
### Training Procedure |
|
Prompt tuning was used: https://huggingface.co/docs/peft/task_guides/prompt_based_methods). |
|
Trained on 2 epochs due to computational limitations. |
|
|
