veerumehta Goto Github PK

bigcode-dataset

bigcode-tools

Set of tools to help working with "Big Code"

code-bert-score

CodeBERTScore: an automatic metric for code generation, based on BERTScore

code-transformer

Implementation of the paper "Language-agnostic representation learning of source code from structure and context".

code2seq

Code for the model presented in the paper: "code2seq: Generating Sequences from Structured Representations of Code"

code_tokenize

Fast tokenization and structural analysis of any programming language

codesearchnet

Datasets, tools, and benchmarks for representation learning of code.

codetf

CodeTF: One-stop Transformer Library for State-of-the-art Code LLM

codetrans

Pretrained Language Models for Source code

codexglue

CodeXGLUE

developer

with 100k context windows on the way, it's now feasible for every dev to have their own smol developer

dmls-book

Summaries and resources for Designing Machine Learning Systems book (Chip Huyen, O'Reilly 2022)

finetuner

ggml

Tensor library for machine learning

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

graph-ast

A tool to provide the graph representation of the source code based on the paper: "Learning to Represent Program with Graph, ICLR'18"

graph4code

GraphGen4Code: a toolkit for creating code knowledge graphs based on WALA code analysis and extraction of documentation and forum content.

hierarchical-programming-language-mapping

[ICSE'18] Hierarchical Learning of Cross-Language Mappings through Distributed Vector Representations for Code

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

jemma

JEMMA: An Extensible Java dataset for Many ML4Code Applications

langchain

⚡ Building applications with LLMs through composability ⚡

llm-numbers

Numbers every LLM developer should know

magicoder

Magicoder: Source Code Is All You Need

ml4code.github.io

Website for "A Survey of Machine Learning for Big Code and Naturalness"

multilang-code-datasets

Multiple language specific code datasets

netflix-1080p

Chrome extension to play Netflix in 1080p and 5.1

neuralcodesum

Official implementation of our work, A Transformer-based Approach for Source Code Summarization [ACL 2020].

nlp-for-hindi

State of the Art Language models and Classifier for Hindi language (spoken in Indian sub-continent)

odex

plbart

Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].