Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

Qodo-Cover: An AI-Powered Tool for Automated Test Generation and Code Coverage Enhancement! 💻🤖🧪🐞

Agentless🐱: an agentless approach to automatically solve software development problems

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

aider is AI pair programming in your terminal

[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

Practicing system design on a simple three-in-a-row game

LLM101n: Let's build a Storyteller

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Pure Python 3 MTProto API Telegram client library, for bots too!

Russian/English/Estonian/Finnish/Swedish phonetic algorithm based on Soundex and Metaphone

Speech Emotion Recognition

fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backend.

Faster Whisper transcription with CTranslate2

InstantNGP with depth supervision experiments

Generative adversarial approach to most popular NLP tasks

The AI Knowledge Editor

Web-scale retrieval for knowledge-intensive NLP

Blazing fast framework for fine-tuning similarity learning models

Multitask NLU architecture for text and token classification tasks.

Generative adversarial approach to text classification

A collection of my data science articles published in Towards Data Science and Towards AI.

Collection of papers and resources for data augmentation for NLP.

PyTorch implementations of Generative Adversarial Networks.

Simple project on html anonymization

This is Accent bot. It can score your english accent and give you hints to enhance your pronunciation!

A curated list of resources on document similarity measures (papers, tutorials, code, ...)

A game theoretic approach to explain the output of any machine learning model.