---
title: incoder-1B
canonical_url: "https://www.modelscope.cn/models/facebook/incoder-1B"
md_url: "https://www.modelscope.cn/models/facebook/incoder-1B.md"
repository: facebook/incoder-1B
last_updated: 2025-05-20
license: cc-by-nc-4.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - xglm
architectures:
  - XGLMForCausalLM
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 331
stars: 0
tags:
  - code
  - python
  - javascript
---

# incoder-1B

> incoder-1B - facebook 在 ModelScope 开源的模型。A 1B parameter decoder-only Transformer model trained on code using a causal-masked objective, which allows inserting/infilling code as well as standard left-to-right generation.

facebook/incoder-1B 是 ModelScope 魔搭社区上的text-generation模型，采用 cc-by-nc-4.0 许可。

- **Repository**: facebook/incoder-1B
- **License**: cc-by-nc-4.0
- **Tasks**: text-generation
- **Tags**: code, python, javascript
- **Downloads**: 331
- **Stars**: 0
- **Last updated**: 2025-05-20

Source: https://www.modelscope.cn/models/facebook/incoder-1B

---

# InCoder 1B

A 1B parameter decoder-only Transformer model trained on code using a causal-masked objective, which allows inserting/infilling code as well as standard left-to-right generation.

The model was trained on public open-source repositories with a permissive, non-copyleft, license (Apache 2.0, MIT, BSD-2 or BSD-3) from GitHub and GitLab, as well as StackOverflow. Repositories primarily contained Python and JavaScript, but also include code from 28 languages, as well as StackOverflow. 

For more information, see our:

- [Demo](https://huggingface.co/spaces/facebook/incoder-demo)
- [Project site](https://sites.google.com/view/incoder-code-models)
- [Examples](https://sites.google.com/view/incoder-code-models/home/examples)
- [Paper](https://arxiv.org/abs/2204.05999)

A larger, 6B, parameter model is also available at [facebook/incoder-6B](https://huggingface.co/facebook/incoder-6B).

## Requirements

`pytorch`, `tokenizers`, and `transformers`. Our model requires HF's tokenizers >= 0.12.1, due to changes in the pretokenizer.

```
pip install torch
pip install "tokenizers>=0.12.1"
pip install transformers
```

## Usage

See [https://github.com/dpfried/incoder](https://github.com/dpfried/incoder) for example code.

### Model
`model = AutoModelForCausalLM.from_pretrained("facebook/incoder-1B")`

### Tokenizer
`tokenizer = AutoTokenizer.from_pretrained("facebook/incoder-1B")`

(Note: the incoder-1B and incoder-6B tokenizers are identical, so 'facebook/incoder-6B' could also be used.)

When calling `tokenizer.decode`, it's important to pass `clean_up_tokenization_spaces=False` to avoid removing spaces after punctuation. For example:

`tokenizer.decode(tokenizer.encode("from ."), clean_up_tokenization_spaces=False)`

(Note: encoding prepends the `<|endoftext|>` token, as this marks the start of a document to our model. This token can be removed from the decoded output by passing `skip_special_tokens=True` to `tokenizer.decode`.)

## License

CC-BY-NC 4.0

## Credits

The model was developed by Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer and Mike Lewis.

Thanks to Lucile Saulnier, Leandro von Werra, Nicolas Patry, Suraj Patil, Omar Sanseviero, and others at HuggingFace for help with the model release, and to Naman Goyal and Stephen Roller for the code our demo was based on!