README.md

---
tags:
- ctranslate2
- int8
- float16

license: bsd-3-clause
---
# # Fast-Inference with Ctranslate2
Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.

quantized version of [Salesforce/codegen-6B-multi](https://huggingface.co/Salesforce/codegen-6B-multi)
```bash
pip install hf-hub-ctranslate2>=2.0.8 
```
Converted on 2023-05-21 using
```
ct2-transformers-converter --model Salesforce/codegen-6B-multi --output_dir /home/michael/tmp-ct2fast-codegen-6B-multi --force --copy_files merges.txt tokenizer.json README.md tokenizer_config.json vocab.json special_tokens_map.json added_tokens.json .gitattributes --quantization float16
```

Checkpoint compatible to [ctranslate2>=3.13.0](https://github.com/OpenNMT/CTranslate2) and [hf-hub-ctranslate2>=2.0.6](https://github.com/michaelfeil/hf-hub-ctranslate2)
- `compute_type=int8_float16` for `device="cuda"` 
- `compute_type=int8`  for `device="cpu"`

```python
from hf_hub_ctranslate2 import TranslatorCT2fromHfHub, GeneratorCT2fromHfHub
from transformers import AutoTokenizer

model_name = "michaelfeil/ct2fast-codegen-6B-multi"
# use either TranslatorCT2fromHfHub or GeneratorCT2fromHfHub here, depending on model.
model = GeneratorCT2fromHfHub(
        # load in int8 on CUDA
        model_name_or_path=model_name, 
        device="cuda",
        compute_type="int8_float16",
        # tokenizer=AutoTokenizer.from_pretrained("Salesforce/codegen-6B-multi")
)
outputs = model.generate(
    text=["def print_hello_world():", "def hello_name(name:"],
    max_length=64
)
print(outputs)
```

# Licence and other remarks:
This is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.

# Original description
    
tags:
- ctranslate2
- int8
- float16

# CodeGen (CodeGen-Multi 6B)

## Model description

CodeGen is a family of autoregressive language models for **program synthesis** from the paper: [A Conversational Paradigm for Program Synthesis](https://arxiv.org/abs/2203.13474) by Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, Caiming Xiong. The models are originally released in [this repository](https://github.com/salesforce/CodeGen), under 3 pre-training data variants (`NL`, `Multi`, `Mono`) and 4 model size variants (`350M`, `2B`, `6B`, `16B`).

The checkpoint included in this repository is denoted as **CodeGen-Multi 6B** in the paper, where "Multi" means the model is initialized with *CodeGen-NL 6B* and further pre-trained on a dataset of multiple programming languages, and "6B" refers to the number of trainable parameters.

## Training data

This checkpoint (CodeGen-Multi 6B) was firstly initialized with *CodeGen-NL 6B*, and then pre-trained on [BigQuery](https://console.cloud.google.com/marketplace/details/github/github-repos), a large-scale dataset of multiple programming languages from GitHub repositories. The data consists of 119.2B tokens and includes C, C++, Go, Java, JavaScript, and Python.

## Training procedure

CodeGen was trained using cross-entropy loss to maximize the likelihood of sequential inputs.
The family of models are trained using multiple TPU-v4-512 by Google, leveraging data and model parallelism.
See Section 2.3 of the [paper](https://arxiv.org/abs/2203.13474) for more details.

## Evaluation results

We evaluate our models on two code generation benchmark: HumanEval and MTPB. Please refer to the [paper](https://arxiv.org/abs/2203.13474) for more details.


## Intended Use and Limitations

As an autoregressive language model, CodeGen is capable of extracting features from given natural language and programming language texts, and calculating the likelihood of them.
However, the model is intended for and best at **program synthesis**, that is, generating executable code given English prompts, where the prompts should be in the form of a comment string. The model can complete partially-generated code as well.

## How to use

This model can be easily loaded using the `AutoModelForCausalLM` functionality:

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen-6B-multi")
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen-6B-multi")

text = "def hello_world():"
input_ids = tokenizer(text, return_tensors="pt").input_ids

generated_ids = model.generate(input_ids, max_length=128)
print(tokenizer.decode(generated_ids[0], skip_special_tokens=True))
```

## BibTeX entry and citation info

```bibtex
@article{Nijkamp2022ACP,
  title={A Conversational Paradigm for Program Synthesis},
  author={Nijkamp, Erik and Pang, Bo and Hayashi, Hiroaki and Tu, Lifu and Wang, Huan and Zhou, Yingbo and Savarese, Silvio and Xiong, Caiming},
  journal={arXiv preprint},
  year={2022}
}
```