---
pipeline_tag: text-generation
inference: true
widget:
- text: 'def print_hello_world():'
  example_title: Hello world
  group: Python
- text: 'Gradient descent is'
  example_title: Machine Learning
  group: English
- license: bigcode-openrail-m
datasets:
- bigcode/the-stack-dedup
- tiiuae/falcon-refinedweb
metrics:
- code_eval
- mmlu
- arc
- hellaswag
- truthfulqa
library_name: transformers
tags:
- code
model-index:
- name: StarCoderPlus
  results:
  - task:
      type: text-generation
    dataset:
      type: openai_humaneval
      name: HumanEval (Prompted)
    metrics:
    - name: pass@1
      type: pass@1
      value: 26.7
      verified: false
  - task:
      type: text-generation
    dataset:
      type: MMLU (5-shot)
      name: MMLU
    metrics:
    - name: Accuracy
      type: Accuracy
      value: 45.1
      verified: false
  - task:
      type: text-generation
    dataset:
      type: HellaSwag (10-shot)
      name: HellaSwag
    metrics:
    - name: Accuracy
      type: Accuracy
      value: 77.3
      verified: false
  - task:
      type: text-generation
    dataset:
      type: ARC (25-shot)
      name: ARC
    metrics:
    - name: Accuracy
      type: Accuracy
      value: 48.9
      verified: false
  - task:
      type: text-generation
    dataset:
      type: ThrutfulQA (0-shot)
      name: ThrutfulQA
    metrics:
    - name: Accuracy
      type: Accuracy
      value: 37.9
      verified: false
extra_gated_prompt: >-
  ## Model License Agreement

  Please read the BigCode [OpenRAIL-M
  license](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement)
  agreement before accepting it.
    
extra_gated_fields:
  I accept the above license agreement, and will use the Model complying with the set of use restrictions and sharing requirements: checkbox
---


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

quantized version of [bigcode/starcoderplus](https://huggingface.co/bigcode/starcoderplus)
```bash
pip install hf-hub-ctranslate2>=2.0.10 ctranslate2>=3.16.0
```
Converted on 2023-06-18 using
```
ct2-transformers-converter --model bigcode/starcoderplus --output_dir ./ct2fast-starcoder --force --copy_files merges.txt tokenizer.json README.md tokenizer_config.json vocab.json generation_config.json special_tokens_map.json .gitattributes --quantization int8_float16 --trust_remote_code
```

Checkpoint compatible to [ctranslate2>=3.16.0](https://github.com/OpenNMT/CTranslate2)
and [hf-hub-ctranslate2>=2.0.10](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 = "piratos/ct2fast-starcoderplus"
# 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("bigcode/starcoderplus")
)
outputs = model.generate(
    text=["def fibonnaci(", "User: How are you doing? Bot:"],
    max_length=64,
    include_prompt_in_result=False
)
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
    
# StarCoderPlus

Play with the instruction-tuned StarCoderPlus at [StarChat-Beta](https://huggingface.co/spaces/HuggingFaceH4/starchat-playground).

##  Table of Contents

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

## Model Summary

StarCoderPlus is a fine-tuned version of [StarCoderBase](https://huggingface.co/bigcode/starcoderbase) on 600B tokens from the English web dataset [RedefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) 
combined with [StarCoderData](https://huggingface.co/datasets/bigcode/starcoderdata) from [The Stack (v1.2)](https://huggingface.co/datasets/bigcode/the-stack) and a Wikipedia dataset.
It's a 15.5B parameter Language Model trained on English and 80+ programming languages. The model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150),
[a context window of 8192 tokens](https://arxiv.org/abs/2205.14135),  and was trained using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255) on 1.6 trillion tokens. 

- **Repository:** [bigcode/Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
- **Project Website:** [bigcode-project.org](https://www.bigcode-project.org)
- **Point of Contact:** [contact@bigcode-project.org](mailto:contact@bigcode-project.org)
- **Languages:** English & 80+ Programming languages


## Use

### Intended use

The model was trained on English and GitHub code. As such it is _not_ an instruction model and commands like "Write a function that computes the square root." do not work well. However, the instruction-tuned version in [StarChat](hhttps://huggingface.co/spaces/HuggingFaceH4/starchat-playground) makes a capable assistant.

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

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

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

tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)

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-middle uses special tokens to identify the prefix/middle/suffix 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]))
```

### Attribution & Other Requirements

The training code dataset of the model was filtered for permissive licenses only. Nevertheless, the model can generate source code verbatim from the dataset. The code's license might require attribution and/or other specific requirements that must be respected. We provide a [search index](https://huggingface.co/spaces/bigcode/starcoder-search) 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 a mixture of English text from the web and GitHub code. Therefore it might encounter limitations when working with non-English text, and can carry the stereotypes and biases commonly encountered online.
Additionally, the generated code should be used with caution as it may contain errors, inefficiencies, or potential vulnerabilities. For a more comprehensive understanding of the base model's code limitations, please refer to See [StarCoder paper](hhttps://arxiv.org/abs/2305.06161). 

# Training
StarCoderPlus is a fine-tuned version on 600B English and code tokens of StarCoderBase, which was pre-trained on 1T code tokens. Below are the fine-tuning details:

## Model
- **Architecture:** GPT-2 model with multi-query attention and Fill-in-the-Middle objective
- **Finetuning steps:** 150k
- **Finetuning tokens:** 600B
- **Precision:** bfloat16

## Hardware

- **GPUs:** 512 Tesla A100
- **Training time:** 14 days

## Software

- **Orchestration:** [Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
- **Neural networks:** [PyTorch](https://github.com/pytorch/pytorch)
- **BP16 if applicable:** [apex](https://github.com/NVIDIA/apex)

# License
The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement [here](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement).