# Mistral-7B SQL Model (Saved)

This folder contains the tokenizer and either full model weights or LoRA adapters.

## Loading

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

model_path = '/content/drive/MyDrive/mistral7b_sql_model'
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.bfloat16, device_map='auto')
```