%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Starcoder
StarCoder is a 15.5B-parameter code generation model trained on over 80 programming languages, supporting a context window of 8192 tokens
Downloads 10.72k
Release Time : 4/24/2023
Model Overview
StarCoder is a powerful code generation model trained on The Stack dataset, capable of generating code snippets in multiple programming languages. It employs multi-query attention and fill-in-the-middle objective techniques, trained on 1 trillion tokens.
Model Features
Large context window
Supports 8192-token context window, ideal for processing long code snippets
Multilingual support
Trained on 80+ programming languages including Python, Java, C++ and other mainstream languages
Fill-in-the-middle generation
Supports fill-in-the-middle (FIM) technique to complete missing parts in code
High performance
Excellent performance on benchmarks like HumanEval with pass@1 score reaching 0.408
Model Capabilities
Code autocompletion
Code snippet generation
Multilingual code conversion
Code documentation generation
Code error fixing
Use Cases
Software development
Function generation
Automatically generates implementation code based on function signatures
Achieved pass@1 score of 0.336 in HumanEval test
Code completion
Provides intelligent code completion suggestions in IDEs
Education
Programming learning assistance
Generates example code or explains programming concepts for students
pipeline_tag: text-generation inference: true widget:
-
text: 'def print_hello_world():' example_title: Hello world group: Python license: bigcode-openrail-m datasets:
-
bigcode/the-stack-dedup metrics:
-
code_eval library_name: transformers tags:
-
code model-index:
-
name: StarCoder results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval (Prompted)
metrics:
- name: pass@1 type: pass@1 value: 0.408 verified: false
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1 type: pass@1 value: 0.336 verified: false
- task:
type: text-generation
dataset:
type: mbpp
name: MBPP
metrics:
- name: pass@1 type: pass@1 value: 0.527 verified: false
- task:
type: text-generation
dataset:
type: ds1000
name: DS-1000 (Overall Completion)
metrics:
- name: pass@1 type: pass@1 value: 0.26 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (C++)
metrics:
- name: pass@1 type: pass@1 value: 0.3155 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (C#)
metrics:
- name: pass@1 type: pass@1 value: 0.2101 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (D)
metrics:
- name: pass@1 type: pass@1 value: 0.1357 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Go)
metrics:
- name: pass@1 type: pass@1 value: 0.1761 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Java)
metrics:
- name: pass@1 type: pass@1 value: 0.3022 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Julia)
metrics:
- name: pass@1 type: pass@1 value: 0.2302 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (JavaScript)
metrics:
- name: pass@1 type: pass@1 value: 0.3079 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Lua)
metrics:
- name: pass@1 type: pass@1 value: 0.2389 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (PHP)
metrics:
- name: pass@1 type: pass@1 value: 0.2608 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Perl)
metrics:
- name: pass@1 type: pass@1 value: 0.1734 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Python)
metrics:
- name: pass@1 type: pass@1 value: 0.3357 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (R)
metrics:
- name: pass@1 type: pass@1 value: 0.155 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Ruby)
metrics:
- name: pass@1 type: pass@1 value: 0.0124 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Racket)
metrics:
- name: pass@1 type: pass@1 value: 0.0007 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Rust)
metrics:
- name: pass@1 type: pass@1 value: 0.2184 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Scala)
metrics:
- name: pass@1 type: pass@1 value: 0.2761 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Bash)
metrics:
- name: pass@1 type: pass@1 value: 0.1046 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (Swift)
metrics:
- name: pass@1 type: pass@1 value: 0.2274 verified: false
- task:
type: text-generation
dataset:
type: nuprl/MultiPL-E
name: MultiPL-HumanEval (TypeScript)
metrics:
- name: pass@1 type: pass@1 value: 0.3229 verified: false extra_gated_prompt: >-
Model License Agreement
Please read the BigCode OpenRAIL-M license agreement before accepting it.
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval (Prompted)
metrics:
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
StarCoder
Play with the model on the StarCoder Playground.
Table of Contents
Model Summary
The StarCoder models are 15.5B parameter models trained on 80+ programming languages from The Stack (v1.2), with opt-out requests excluded. The model uses Multi Query Attention, a context window of 8192 tokens, and was trained using the Fill-in-the-Middle objective on 1 trillion tokens.
- Repository: bigcode/Megatron-LM
- Project Website: bigcode-project.org
- Paper: 💫StarCoder: May the source be with you!
- Point of Contact: contact@bigcode-project.org
- Languages: 80+ Programming languages
Use
Intended use
The model was trained on 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, by using the Tech Assistant prompt you can turn it into a capable technical assistant.
Feel free to share your generations in the Community tab!
Generation
# pip install -q transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "bigcode/starcoder"
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 pretraining 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 source code from 80+ programming languages. The predominant natural language in source code is English although other languages are also present. As such the model is capable of generating code snippets provided some context but the generated code is not guaranteed to work as intended. It can be inefficient, contain bugs or exploits. At this time there is no mechanism to detect content previously generated by the model. See the paper for an in-depth discussion of the model limitations.
Training
Model
- Architecture: GPT-2 model with multi-query attention and Fill-in-the-Middle objective
- Pretraining steps: 250k
- Pretraining tokens: 1 trillion
- Precision: bfloat16
Hardware
- GPUs: 512 Tesla A100
- Training time: 24 days (320,256 GPU hours pretraining + 11,208 GPU hours Python fine-tuning)
- Training FLOPS: 8.46E+22
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.
Email contact@bigcode-project.org with questions related to the license agreement and for appeals relating to use restrictions.
Citation
@article{li2023starcoder,
title={StarCoder: may the source be with you!},
author={Raymond Li and Loubna Ben Allal and Yangtian Zi and Niklas Muennighoff and Denis Kocetkov and Chenghao Mou and Marc Marone and Christopher Akiki and Jia Li and Jenny Chim and Qian Liu and Evgenii Zheltonozhskii and Terry Yue Zhuo and Thomas Wang and Olivier Dehaene and Mishig Davaadorj and Joel Lamy-Poirier and João Monteiro and Oleh Shliazhko and Nicolas Gontier and Nicholas Meade and Armel Zebaze and Ming-Ho Yee and Logesh Kumar Umapathi and Jian Zhu and Benjamin Lipkin and Muhtasham Oblokulov and Zhiruo Wang and Rudra Murthy and Jason Stillerman and Siva Sankalp Patel and Dmitry Abulkhanov and Marco Zocca and Manan Dey and Zhihan Zhang and Nour Fahmy and Urvashi Bhattacharyya and Wenhao Yu and Swayam Singh and Sasha Luccioni and Paulo Villegas and Maxim Kunakov and Fedor Zhdanov and Manuel Romero and Tony Lee and Nadav Timor and Jennifer Ding and Claire Schlesinger and Hailey Schoelkopf and Jan Ebert and Tri Dao and Mayank Mishra and Alex Gu and Jennifer Robinson and Carolyn Jane Anderson and Brendan Dolan-Gavitt and Danish Contractor and Siva Reddy and Daniel Fried and Dzmitry Bahdanau and Yacine Jernite and Carlos Muñoz Ferrandis and Sean Hughes and Thomas Wolf and Arjun Guha and Leandro von Werra and Harm de Vries},
year={2023},
eprint={2305.06161},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
Phi 2 GGUF
Other
Phi-2 is a small yet powerful language model developed by Microsoft, featuring 2.7 billion parameters, focusing on efficient inference and high-quality text generation.
Large Language Model Supports Multiple Languages
P
TheBloke
41.5M
205
Roberta Large
MIT
A large English language model pre-trained with masked language modeling objectives, using improved BERT training methods
Large Language Model English
R
FacebookAI
19.4M
212
Distilbert Base Uncased
Apache-2.0
DistilBERT is a distilled version of the BERT base model, maintaining similar performance while being more lightweight and efficient, suitable for natural language processing tasks such as sequence classification and token classification.
Large Language Model English
D
distilbert
11.1M
669
Llama 3.1 8B Instruct GGUF
Meta Llama 3.1 8B Instruct is a multilingual large language model optimized for multilingual dialogue use cases, excelling in common industry benchmarks.
Large Language Model English
L
modularai
9.7M
4
Xlm Roberta Base
MIT
XLM-RoBERTa is a multilingual model pretrained on 2.5TB of filtered CommonCrawl data across 100 languages, using masked language modeling as the training objective.
Large Language Model Supports Multiple Languages
X
FacebookAI
9.6M
664
Roberta Base
MIT
An English pre-trained model based on Transformer architecture, trained on massive text through masked language modeling objectives, supporting text feature extraction and downstream task fine-tuning
Large Language Model English
R
FacebookAI
9.3M
488
Opt 125m
Other
OPT is an open pre-trained Transformer language model suite released by Meta AI, with parameter sizes ranging from 125 million to 175 billion, designed to match the performance of the GPT-3 series while promoting open research in large-scale language models.
Large Language Model English
O
facebook
6.3M
198
1
A pretrained model based on the transformers library, suitable for various NLP tasks
Large Language Model
Transformers
Transformers1
unslothai
6.2M
1
Llama 3.1 8B Instruct
Llama 3.1 is Meta's multilingual large language model series, featuring 8B, 70B, and 405B parameter scales, supporting 8 languages and code generation, with optimized multilingual dialogue scenarios.
Large Language Model Transformers Supports Multiple Languages
Transformers Supports Multiple LanguagesL
meta-llama
5.7M
3,898
T5 Base
Apache-2.0
The T5 Base Version is a text-to-text Transformer model developed by Google with 220 million parameters, supporting multilingual NLP tasks.
Large Language Model Supports Multiple Languages
T
google-t5
5.4M
702
Featured Recommended AI Models