You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model License Agreement

Please read the BigCode OpenRAIL-M license agreement before accepting it.

YAML Metadata Error: "model-index[0].results[1].dataset.type" with value "MMLU (5-shot)" fails to match the required pattern: /^(?:[\w-]+\/)?[\w-.]+$/

YAML Metadata Error: "model-index[0].results[2].dataset.type" with value "HellaSwag (10-shot)" fails to match the required pattern: /^(?:[\w-]+\/)?[\w-.]+$/

YAML Metadata Error: "model-index[0].results[3].dataset.type" with value "ARC (25-shot)" fails to match the required pattern: /^(?:[\w-]+\/)?[\w-.]+$/

YAML Metadata Error: "model-index[0].results[4].dataset.type" with value "ThrutfulQA (0-shot)" fails to match the required pattern: /^(?:[\w-]+\/)?[\w-.]+$/

StarCoderPlus

Play with the instruction-tuned StarCoderPlus at StarChat-Beta.

Model Summary
Use
Limitations
Training
License

Model Summary

StarCoderPlus is a fine-tuned version of StarCoderBase on a mix of:

The English web dataset RefinedWeb (1x)
StarCoderData dataset from The Stack (v1.2) (1x)
A Wikipedia dataset that has been upsampled 5 times (5x)

It's a 15.5B parameter Language Model trained on English and 80+ programming languages. The model uses Multi Query Attention, a context window of 8192 tokens, and was trained using the Fill-in-the-Middle objective on 1.6 trillion tokens.

Repository: bigcode/Megatron-LM
Project Website: bigcode-project.org
Point of Contact: [email protected]
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 makes a capable assistant.

Feel free to share your generations in the Community tab!

Generation

# 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:

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 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.

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
Neural networks: PyTorch
BP16 if applicable: apex

License

The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement here.

Downloads last month: 1,499

Model tree for bigcode/starcoderplus

Adapters

2 models

Finetunes

1 model

Quantizations

2 models

Datasets used to train bigcode/starcoderplus

Spaces using bigcode/starcoderplus 32

Collection including bigcode/starcoderplus

⭐ StarCoder

Collection

All models, datasets, and demos related to StarCoder! • 11 items • Updated Feb 27 • 20

Evaluation results

Model card error

This model's model-index metadata is invalid: Schema validation error. "model-index[0].results[1].dataset.type" with value "MMLU (5-shot)" fails to match the required pattern: /^(?:[\w-]+\/)?[\w-.]+$/. "model-index[0].results[2].dataset.type" with value "HellaSwag (10-shot)" fails to match the required pattern: /^(?:[\w-]+\/)?[\w-.]+$/. "model-index[0].results[3].dataset.type" with value "ARC (25-shot)" fails to match the required pattern: /^(?:[\w-]+\/)?[\w-.]+$/. "model-index[0].results[4].dataset.type" with value "ThrutfulQA (0-shot)" fails to match the required pattern: /^(?:[\w-]+\/)?[\w-.]+$/

bigcode
/

starcoderplus