README.md

---
license: apache-2.0
datasets:
- JetBrains/KStack-clean
base_model: meta-llama/CodeLlama-7b-hf
results:
- task:
    type: text-generation
  dataset:
    name: MultiPL-HumanEval (Kotlin)
    type: openai_humaneval
  metrics:
  - name: pass@1
    type: pass@1
    value: 37.89
tags:
- code
---

# Model description

CodeLlama-7B-KStack-clean model is a fine-tuned open-source generative text model fine-tuned on [JetBrains/KStack-clean](https://huggingface.co/datasets/JetBrains/KStack-clean) dataset. 
This is a repository for fine-tuned CodeLlama-7b model in the Hugging Face Transformers format.

# Model use

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load pre-trained model and tokenizer
model_name = 'JetBrains/CodeLlama-7B-KStack-clean'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).to('cuda')

# Create and encode input
input_text = """\
This function takes an integer n and returns factorial of a number:
fun factorial(n: Int): Int {\
"""
input_ids = tokenizer.encode(
    input_text, return_tensors='pt'
).to('cuda')

# Generate
output = model.generate(
    input_ids, max_length=60, num_return_sequences=1, 
    pad_token_id=tokenizer.eos_token_id
)

# Decode output
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
print(generated_text)
```

As with the base model, we can use FIM. To do this, the following format must be used: 
```
'<PRE> ' + prefix + ' <SUF> ' + suffix + ' <MID>'
```

# Training setup

The model was trained on one A100 GPU with following hyperparameters:

|         **Hyperparameter**           |             **Value**              |
|:---------------------------:|:----------------------------------------:|
|        `warmup`            |           100 steps            |
|        `max_lr`        |          5e-5          |
|        `scheduler`        |          linear          |
|        `total_batch_size`        |        32 (~30K tokens per step)          |
|        `num_epochs`        |          2          |

More details about finetuning can be found in the technical report

# Fine-tuning data

For this model we used 25K exmaples of [KStack-clean](https://huggingface.co/datasets/JetBrains/KStack-clean) selected according to educational value for learning algorithms. In total dataset contains about 23M tokens. 
For more information about the dataset follow the link.

# Evaluation 

To evaluate we used Kotlin Humaneval ([more infromation here](https://huggingface.co/datasets/JetBrains/Kotlin_HumanEval))

Fine-tuned model:

|         **Model name**           |             **Kotlin HumanEval Pass Rate**              |
|:---------------------------:|:----------------------------------------:|
|           `base model`            |           26.89            |
|        `fine-tuned model`        |          37.89        |

# Ethical Considerations and Limitations

CodeLlama-7B-KStack-clean and its variants are a new technology that carries risks with use. The testing conducted to date could not cover all scenarios. For these reasons, as with all LLMs, CodeLlama-7B-KStack-clean potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. The model was fine-tuned on a specific data format (Kotlin tasks), and deviation from this format can also lead to inaccurate or undesirable responses to user queries. Therefore, before deploying any applications of CodeLlama-7B-KStack-clean, developers should perform safety testing and tuning tailored to their specific applications of the model.