README.md

---
license: other
language:
- code
programming_language: 
- Java
- JavaScript
- Python
pipeline_tag: text-generation
widget:
- text: 'def print_hello_world():'
  example_title: Hello world
  group: Python

model-index:
- name: SantaCoder
  results:
  - task:
      type: text-generation
    dataset:
      type: openai_humaneval
      name: HumanEval (Python)
    metrics:
    - name: pass@1
      type: pass@1
      value: 0.0
      verified: false
    - name: pass@10
      type: pass@10
      value: 0.0
      verified: false
    - name: pass@100
      type: pass@100
      value: 0.0
      verified: false
  - task:
      type: text-generation
    dataset:
      type: nuprl/MultiPL-E
      name: MultiPL HumanEval (Java)
    metrics:
    - name: pass@1
      type: pass@1
      value: 0.0
      verified: false
    - name: pass@10
      type: pass@10
      value: 0.0
      verified: false
    - name: pass@100
      type: pass@100
      value: 0.0
  - task:
      type: text-generation
    dataset:
      type: nuprl/MultiPL-E
      name: MultiPL HumanEval (JavaScript)
    metrics:
    - name: pass@1
      type: pass@1
      value: 0.0
      verified: false
    - name: pass@10
      type: pass@10
      value: 0.0
      verified: false
    - name: pass@100
      type: pass@100
      value: 0.0
  - task:
      type: text-generation
    dataset:
      type: openai_humaneval
      name: MBPP (Python)
    metrics:
    - name: pass@1
      type: pass@1
      value: 0.0
      verified: false
    - name: pass@10
      type: pass@10
      value: 0.0
      verified: false
    - name: pass@100
      type: pass@100
      value: 0.0
      verified: false
  - task:
      type: text-generation
    dataset:
      type: nuprl/MultiPL-E
      name: MultiPL MBPP (Java)
    metrics:
    - name: pass@1
      type: pass@1
      value: 0.0
      verified: false
    - name: pass@10
      type: pass@10
      value: 0.0
      verified: false
    - name: pass@100
      type: pass@100
      value: 0.0
  - task:
      type: text-generation
    dataset:
      type: nuprl/MultiPL-E
      name: MultiPL MBPP (JavaScript)
    metrics:
    - name: pass@1
      type: pass@1
      value: 0.0
      verified: false
    - name: pass@10
      type: pass@10
      value: 0.0
      verified: false
    - name: pass@100
      type: pass@100
      value: 0.0
  - task:
      type: text-generation
    dataset:
      type: loubnabnl/humaneval_infilling
      name: HumanEval FIM (Python)
    metrics:
    - name: pass@1
      type: pass@1
      value: 0.0
      verified: false
    - name: pass@10
      type: pass@10
      value: 0.0
      verified: false
    - name: pass@100
      type: pass@100
      value: 0.0
      verified: false
  - task:
      type: text-generation
    dataset:
      type: nuprl/MultiPL-E
      name: MultiPL HumanEval FIM (Java)
    metrics:
    - name: pass@1
      type: pass@1
      value: 0.0
      verified: false
    - name: pass@10
      type: pass@10
      value: 0.0
      verified: false
    - name: pass@100
      type: pass@100
      value: 0.0
  - task:
      type: text-generation
    dataset:
      type: nuprl/MultiPL-E
      name: MultiPL HumanEval FIM (JavaScript)
    metrics:
    - name: pass@1
      type: pass@1
      value: 0.0
      verified: false
    - name: pass@10
      type: pass@10
      value: 0.0
      verified: false
    - name: pass@100
      type: pass@100
      value: 0.0
  - task:
      type: text-generation
    dataset:
      type: code_x_glue_ct_code_to_text
      name: CodeXGLUE code-to-text (Python)
    metrics:
    - name: BLEU
      type: bleu
      value: 0.0
      verified: false
---

# SantaCoder

![banner](https://huggingface.co/datasets/bigcode/admin/resolve/main/banner.png)

#  Table of Contents

1. [Model Summary](#model-summary)
2. [Use](#use)
3. [Limitations](#limitations)
4. [Training](#training)
5. [Citation](#citation)

# Model Summary

The SantaCoder models are a series of 1B parameter models trained on Python, Java, and JavaScript. They were trained on datasets with different filter parameters and with architecture and objective variations. The main model uses multi-query attention, was trained using near-deduplication and commnent-to-code ratio as filtering criteria and using the Fill-in-the-Middle objective.

- **Repository:** [bigcode/Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
- **Project Website:** [bigcode-project.org]www.bigcode-project.org)
- **Paper:** [Coming soon]()
- **Point of Contact:** [contact@bigcode-project.org](mailto:contact@bigcode-project.org)
- **Languages:** Python, Java, and JavaScript

|Model|Architecture|Objective|Filtering|
|:-|:-|:-|:-|:-|
|`mha`|MHA|AR + FIM| Base |
|`no-fim`| MQA | AR| Base |
|`fim`| MQA | AR + FIM | Base |
|`stars`| MQA | AR + FIM | GitHub stars |
|`fertility`| MQA | AR + FIM | Tokenizer fertility |
|`comments`| MQA | AR + FIM | Comment-to-code ratio |
|`dedup-alt`| MQA | AR + FIM | Stronger near-deduplication |
|`dedup-alt-comments`| MQA | AR + FIM | Stronger near-deduplication and comment-to-code ratio |

The `dedup-alt-comments` model is the best performing model and was trained twice as long as the others. This checkpoint is available here on the `main` 

# Use

## Intended use



**Feel free to share your generations in the Community tab!**

## How to use

### Generation
```python
# pip install -q transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint = "bigcode/santacoder"
device = "cuda" # for GPU usage or "cpu" for CPU usage

tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint, trust_remote_code=True).to()

inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```

### Fill-in-the-middle
Fill-in-the-mid uses special tokens to identify the prefix/middle/suffic part of the input and output:

```python
input_text = "<fim-prefix>def print_hello_world():\n    <fim-suffix>\n    print("Hello world!")<fim-middle>
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```

### Load other checkpoints
We upload the checkpoint of each experiment to a seperate branch as well as the intermediate checkpoints as commits on the branches. You can load them with the `revision` flag:

```python
checkpoint = "bigcode/santacoder"
revision = "no-fim" # name of branch or commit hash

model = AutoModelForCausalLM.from_pretrained(checkpoint, revision=revision, trust_remote_code=True).to(device)
```

### Attribution

The pretraining dataset of the model was filtered for permissive licenses only. Nevertheless, the model can generate source code verbatim from the dataset which requires attribution. We provide a [search index](TODO) that let's you search through the pretraining data to identify where generated code came from and apply the proper attribution to your code.

# Limitations

The model has been trained on source code in Python, Java, and JavaScript. The predominant language in source is English although other languages are also present. As such the model is capable to generate code snippets provided some context but the generated code is not guaranteed to work as intended. It can be inefficient, contain bugs or exploits.

# Training

## Model

- **Architecture:** GPT-2 model with multi-query attention and Fill-in-the-Middle objective
- **Pretraining steps:** 600K
- **Pretraining tokens:** 236 billion
- **Precision:** float16

## Hardware

- **GPUs:** 96 Tesla V100
- **Training time:** 6.2 days
- **Total FLOPS:** 2.1 x 10e21

## Software

- **Orchestration:** [Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
- **Neural networks:** [PyTorch](https://github.com/pytorch/pytorch)
- **FP16 if applicable:** [apex](https://github.com/NVIDIA/apex)


# Citation
**TODO**