---
library_name: transformers
datasets:
- Nikil263/Fine_Tuning_Dataset
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->



## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

The fine-tuned model "Nikil263/Fine_Tuned_GPT2model" has been specifically fine-tuned to enhance its performance in generating constraints for Pyomo code. This specialized version of the GPT-2 architecture is tailored to understand and produce text relevant to defining and adding constraints in Pyomo, a popular Python-based optimization modeling language.

Through the fine-tuning process, the model has been trained on a dataset that includes various examples of Pyomo constraints, enabling it to accurately generate syntactically correct and contextually appropriate constraint expressions.

## Training Details

### Fine Tuning

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

The fine-tuning dataset for "Nikil263/Fine_Tuned_GPT2model" consists of a collection of natural language instructions and corresponding Pyomo code snippets specifically focused on defining and adding constraints in optimization models. Each entry in the dataset pairs an instructional prompt, such as "add a constraint of 7X + 3Y >= -7 in our model," with the appropriate Pyomo code, e.g., model.constraint3 = Constraint(expr=7 * model.x + 3 * model.y >= -7). This curated dataset ensures that the model learns to generate accurate and contextually relevant Pyomo constraint code from natural language descriptions, facilitating the automation of optimization model setup.

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

The testing data was made with 100 random constrainsts in the same format like fine tuning dataset.



#### Metrics

Accuracy: 72.00%

Average BLEU Score: 0.8894