# 🧠 Code Generation Model – Fine-Tuned `Salesforce/codegen-350M-multi`

This repository contains a fine-tuned version of the [`Salesforce/codegen-350M-multi`](https://huggingface.co/Salesforce/codegen-350M-multi) model. It generates code snippets based on natural language or function signature prompts.

---

## 📦 Base Model

- **Model**: `Salesforce/codegen-350M-multi`
- **Architecture**: Causal LM (Decoder-only Transformer)
- **Parameters**: ~350M
- **Supports**: Python, JavaScript, Java, and more
- **Quantized**: ✅ FP16 using `bitsandbytes` (optional)

---

## 📚 Dataset

### Dataset: [code_x_glue_cc_code_to_text](https://huggingface.co/datasets/code_x_glue_cc_code_to_text)

- **Source**: Hugging Face Datasets
- **Description**: Dataset of code snippets (in Python) and corresponding natural language docstrings.

```python
from datasets import load_dataset

dataset = load_dataset("code_x_glue_cc_code_to_text", "python")
```

# 📊 Evaluation (Scoring)
Metric: BLEU or CodeBLEU (you can also use exact match, ROUGE, etc.)

```python

from datasets import load_metric

bleu = load_metric("bleu")
bleu_score = bleu.compute(predictions=["generated_code"], references=["reference_code"])
print("BLEU Score:", bleu_score)
```

# 📁 Folder Structure

finetuned_codegen_350M/
├── config.json
├── pytorch_model.bin
├── tokenizer_config.json
├── tokenizer.json
├── special_tokens_map.json
├── vocab.json
├── merges.txt
├── training_args.bin
└── README.md

# 💬 Inference Example

```python

from transformers import pipeline

pipe = pipeline("text-generation", model="./finetuned_codegen_350M", device=0)

prompt = "def is_prime(n):"
result = pipe(prompt, max_length=100, do_sample=True)
print(result[0]["generated_text"])