# sst2_mnli_qqp_LoRA_8

Fine-tuned LLaMA model on SST2 dataset.

- **LoRA**: Enabled
- **LoRA Rank**: 8
- **Tasks**: SST2, MNLI, QQP  
- **Base Model**: [LLaMA 1B (Meta)](https://huggingface.co/meta-llama/Llama-3.2-1B)  
- **Optimizer**: AdamW  
- **Batch Size**: 128
- **Max Sequence Length**: 128 tokens  
- **Tokenizer**: LLaMA-1B tokenizer  

Trained using the 🤗 Transformers `Trainer` API.

## **Usage**
```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("emirhanboge/LLaMA_1B_sst2_mnli_qqp_LoRA_8")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B")
```