đ StarCoderPlus
StarCoderPlus is an instruction - tuned language model. You can interact with it at StarChat - Beta. It offers capabilities in text generation across English and over 80 programming languages, trained on diverse datasets.
đ Quick Start
Play with the instruction - tuned StarCoderPlus at StarChat - Beta.
⨠Features
- Multi - language Support: Trained on English and 80+ programming languages.
- Advanced Architecture: Uses Multi Query Attention, a context window of 8192 tokens, and was trained with the Fill - in - the - Middle objective.
- Fine - tuned Model: Fine - tuned on a mix of high - quality datasets for better performance.
đĻ Installation
No specific installation steps are provided in the original README.
đģ Usage Examples
Basic Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "bigcode/starcoderplus"
device = "cuda"
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]))
Advanced Usage
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]))
đ Documentation
Model Summary
StarCoderPlus is a fine - tuned version of StarCoderBase on a mix of:
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.
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!
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.
đ§ Technical Details
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
đ License
The model is licensed under the BigCode OpenRAIL - M v1 license agreement. You can find the full agreement here.
Additional Information
Property |
Details |
Model Type |
Text - generation |
Training Data |
bigcode/the - stack - dedup, tiiuae/falcon - refinedweb |
Metrics |
code_eval, mmlu, arc, hellaswag, truthfulqa |
Library Name |
transformers |
Tags |
code |
â ī¸ Important Note
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 StarCoder paper.
đĄ Usage Tip
The model is not an instruction model. For better performance with instructions, use the instruction - tuned version in StarChat.