ClaireLee2429/gemma-2b-recipes-lora

Gemma-2B Recipe Generator (LoRA Adapter)

A LoRA fine-tuned adapter for google/gemma-2b trained on recipe data. Given a prompt like "Recipe for chocolate chip cookies:", the model generates structured recipes with ingredients and step-by-step directions.

Why fine-tune?

Gemma-2B is a general-purpose model — it knows about recipes but doesn't reliably produce clean, structured output. Fine-tuning on 5,000 recipes teaches it a consistent format and keeps it focused on the task. Here's a side-by-side comparison:

Base Gemma-2B (no fine-tuning)

Prompt: Recipe for beef tacos:

Recipe for beef tacos:
1 lb ground beef
2 large onion, chopped
1 large tomato, chopped
3-4 fresh jalapeños, sliced
Salt and pepper to taste
1 tbsp olive oil
1 can refried beans
1 can tomato sauce
2-3 cups shredded cheese (I used mozzarella)
1 cup sour cream
1 bag of your favorite taco shells

Heat the olive oil in a large skillet over medium heat. Brown the ground beef,
then drain off excess grease. Add onions, jalapeño, and tomatoes, along with
salt and pepper. Cook until vegetables are softened. Stir in the can of refried
beans and tomato sauce, then remove from heat.

To assemble tacos, place a layer of beef mixture on the bottom of each taco
shell. Top with some shredded cheese, followed by sour cream. Serve with your
favorite taco toppings, such as lettuce, tomatoes, and salsa!

Enjoy!

<h2>What is the most popular Mexican dish?</h2>

The top five Mexican dishes include tacos, burritos, enchiladas, tamales, and nachos.

Fine-tuned model

Prompt: Recipe for beef tacos:

Recipe for beef tacos:
Ingredients:
- 2 lb. ground beef
- 1 can (8 oz.) diced tomatoes
- 1/4 c. chopped onion
- 1/2 tsp. salt
- 1/2 tsp. pepper
- 1/2 tsp. garlic powder
- 1/2 c. water
- 1 can (6 oz.) refried beans
- 1 c. shredded cheese
- 2 flour tortillas

Directions:
- Brown ground beef in a skillet; drain.
- Combine the other ingredients and mix well.
- Pour into a 9 x 5 x 3-inch baking dish.
- Cover with the refried beans and cheese.
- Bake at 350° for 30 minutes.
- Serve with sour cream and lettuce.

Key differences

	Base Gemma-2B	Fine-tuned
Format	No section headers, mixed styles	Consistent Ingredients/Directions structure
Bullet style	None or • bullets	Clean - bullets throughout
Focus	Rambles into commentary, HTML tags, FAQ sections	Stays on-task, recipe only
Measurements	Inconsistent (some missing)	Precise and uniform

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")
model = PeftModel.from_pretrained(base_model, "ClaireLee2429/gemma-2b-recipes-lora")
tokenizer = AutoTokenizer.from_pretrained("ClaireLee2429/gemma-2b-recipes-lora")

prompt = "Recipe for chocolate chip cookies:\n"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7, top_p=0.9, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Sample Output

Prompt: Recipe for chocolate chip cookies:

Recipe for chocolate chip cookies:
Ingredients:
- 1/2 cup butter
- 1/4 cup sugar
- 1/4 cup packed brown sugar
- 3/4 cup flour
- 1/2 teaspoon baking soda
- 1/2 teaspoon salt
- 1 egg
- 1 teaspoon vanilla
- 1/2 cup chocolate chips

Directions:
- In a medium bowl, cream together the butter and sugars.
- Add in the egg and vanilla, mixing until combined.
- In another bowl, whisk together the flour, baking soda and salt.
- Add to the creamed mixture alternately with the chocolate chips, ending with the dry ingredients.
- Stir in gently using a rubber spatula.
- Drop by rounded teaspoonfuls onto ungreased cookie sheets.
- Bake at 350 degrees F for 9 minutes.
- Cool on wire racks before serving.

Prompt: Recipe for pasta carbonara:

Recipe for pasta carbonara:
Ingredients:
- 100 g spaghetti
- 100 g smoked bacon or pancetta
- 250 g mushrooms
- 2 eggs
- 1 tablespoon olive oil
- 1 tablespoon white wine
- 1 teaspoon freshly grated parmesan cheese

Directions:
- Cook the pasta according to package instructions.
- Meanwhile, brown the bacon in a frying pan with some olive oil.
- Add the mushrooms and cook them until they are tender (about 10 minutes).
- Add the cooked pasta to the mushroom mixture along with the eggs and stir well.
- Stir in the wine and then sprinkle over the grated parmesan cheese.
- Season with salt and pepper and serve immediately.

Prompt: Recipe for tomato soup:

Recipe for tomato soup:
Ingredients:
- 1 (28 ounce) can crushed tomatoes
- 1 (4 ounce) can tomato paste
- 1 tablespoon dried basil
- 1/2 tablespoon salt
- 1/2 tablespoon sugar
- 1/2 teaspoon garlic powder
- 1/4 teaspoon red pepper flakes

Directions:
- Combine all ingredients in a large pot and bring to a boil.
- Reduce heat, cover and simmer until thickened, about 1 hour.
- Serve over grilled cheese sandwiches or with tortilla chips.

Training Details

Training Data

corbt/all-recipes -- a dataset of 2.1M recipes scraped from the web. Each example contains a recipe title, ingredients list, and cooking directions in a single input text field.

5,000 recipes were randomly sampled for training, split into:

• Train: 4,500 examples
• Validation: 500 examples

Preprocessing

1. Cleaning: Stripped whitespace, removed empty rows, deduplicated
2. Tokenization: Tokenized with Gemma-2B's tokenizer, padded/truncated to 512 tokens

Training Hyperparameters

Parameter	Value
Method	LoRA (rank 8)
Base model	google/gemma-2b
Epochs	1
Batch size	4
Learning rate	2e-4 (linear decay)
LoRA rank (r)	8
LoRA alpha	16
LoRA dropout	0.05
Target modules	all-linear
Precision	float32 (MPS)
Training regime	fp32 on Apple Silicon (MPS)

Training Results

Metric	Value
Train loss	1.3928
Val loss	1.4030
Val perplexity	4.07
Training time	~1 hr 21 min
Train steps	1,125

Infrastructure

• Hardware: Apple Silicon (MPS)
• Software: Transformers, PEFT 0.18.0, PyTorch 2.9.1
• Orchestration: Dagster pipeline

Pipeline

This adapter was produced by an end-to-end Dagster pipeline:

raw_dataset -> cleaned_dataset -> tokenized_dataset -> train_val_splits -> trained_model

Limitations

• Trained on only 5,000 recipes for 1 epoch -- quality improves with more data/epochs
• Recipes may contain factual inaccuracies (incorrect quantities, missing steps)
• Generation can ramble after the recipe ends -- consider post-processing to truncate
• Not suitable for dietary or safety-critical applications

License

This adapter inherits the Gemma license from the base model.

Framework versions

• PEFT 0.18.0