---
license: mit
tags:
  - text-generation
  - meal-reviews
  - fine-tuned
  - mistral
datasets:
  - shuyangli94/food-com-recipes-and-user-interactions
language:
  - en
base_model: mistralai/Mistral-7B-Instruct-v0.3
---

# Merged Mistral 7B Fine-Tuned for Meal Reviews

## Overview
This repository contains a fine-tuned version of the [Mistral 7B Instruct v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) model, specialized for generating high-quality meal reviews. The model was created by merging a LoRA adapter (available at [Oliver1703dk/meal_review_fine_tuned_adapter_bigger](https://huggingface.co/Oliver1703dk/meal_review_fine_tuned_adapter_bigger)) with the base Mistral 7B model, using the Food.com dataset for fine-tuning.

## Model Details
- **Base Model**: [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3)
- **Fine-Tuning Method**: LoRA (Low-Rank Adaptation), merged with the base model
- **Task**: Text generation for meal reviews
- **Training Data**: The [Food.com Recipes and User Interactions](https://www.kaggle.com/datasets/shuyangli94/food-com-recipes-and-user-interactions) dataset, specifically the user review text. The dataset contains over 700,000 recipe reviews, which were preprocessed to focus on review generation.
- **Training Steps**: 12,714 steps

## Usage
The model can be used directly for inference with the  library. Below is an example of how to load and use the model.

### Installation
```bash
pip install transformers torch
```

### Example Code
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load model and tokenizer
model = AutoModelForCausalLM.from_pretrained(
    "Oliver1703dk/meal_review_merged_mistral_finetuned_bigger",
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Oliver1703dk/meal_review_merged_mistral_finetuned_bigger")

# Inference
prompt = "Write a review for a delicious Italian meal."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_length=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## License
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

## Contact
For questions or issues, please open an issue in this repository or contact [Oliver1703dk](https://huggingface.co/Oliver1703dk).

---
*Generated on April 29, 2025*