Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A wrapper around tensor2tensor to flexibly train, interact, and generate data for neural chatbots.
| Date | Stars |
|---|---|
| 2026-07-24 | 471 |
| 2026-07-25 | 471 |
| 2026-07-28 | 471 |
| 2026-07-30 | 471 |
| 2026-08-06 | 471 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Seq2seqChatbots · [](https://ctt.ac/Zgu6I)
[](https://tdk.bme.hu/VIK/DownloadPaper/asdad) [](https://www.aclweb.org/anthology/P19-1567) [](https://ricsinaruto.github.io/website/docs/acl_poster_h.pdf) [](https://github.com/ricsinaruto/NeuralChatbots-DataFiltering) [](https://github.com/ricsinaruto/dialog-eval) [](https://github.com/ricsinaruto/Seq2seqChatbots/wiki/Chatbot-and-Related-Research-Paper-Notes-with-Images) [](https://github.com/ricsinaruto/Seq2seqChatbots/wiki/API-Documentation) [](https://medium.com/@richardcsaky/neural-chatbots-are-dumb-65b6b40e9bd4)
A wrapper around [tensor2tensor](https://github.com/tensorflow/tensor2tensor) to flexibly train, interact, and generate data for neural chatbots.
The [wiki](https://github.com/ricsinaruto/Seq2seqChatbots/wiki/Chatbot-and-Related-Research-Paper-Notes-with-Images) contains my notes and summaries of over 150 recent publications related to neural dialog modeling.
## Features
:floppy_disk: Run your own trainings or experiment with pre-trained models
:white_check_mark: 4 different dialog datasets integrated with tensor2tensor
:twisted_rightwards_arrows: Seemlessly works with any model or hyperparameter set in tensor2tensor
:rocket: Easily extendable base class for dialog problems
## Setup
Run setup.py which installs required packages and steps you through downloading additional data:
```
python setup.py
```
You can download all trained models used in [this](https://www.aclweb.org/anthology/P19-1567) paper from [here](https://mega.nz/#!mI0iDCTI!qhKoBiQRY3rLg3K6nxAmd4ZMNEX4utFRvSby_0q2dwU). Each training contains two checkpoints, one for the validation loss minimum and another after 150 epochs. The data and the trainings folder structure match each other exactly.
## Usage
```
python t2t_csaky/main.py --mode=train
```
The mode argument can be one of the following four: *{[generate_data](https://github.com/ricsinaruto/Seq2seqChatbots/tree/master#generate-data), [train](https://github.com/ricsinaruto/Seq2seqChatbots/tree/master#train), [decode](https://github.com/ricsinaruto/Seq2seqChatbots/tree/master#decode), experiment}*. In the *experiment* mode you can speficy what to do inside the *experiment* function of the *[run](https://github.com/ricsinaruto/Seq2seqChatbots/blob/master/t2t_csaky/utils/run.py)* file. A detailed explanation is given below, for what each mode does.
### Config
You can control the flags and parameters of each mode directly in this [file](https://github.com/ricsinaruto/Seq2seqChatbots/blob/master/t2t_csaky/config.py). For each run that you initiate this file will be copied to the appropriate directory, so you can quickly access the parameters of any run. There are some flags that you have to set for every mode (the *FLAGS* dictionary in the config file):
* **t2t_usr_dir**: Path to the directory where my code resides. You don't have to change this, unless you rename the directory.
* **data_dir**: The path to the directory where you want to generate the source and target pairs, and other data. The dataset will be downloaded one level higher from this directory into a *raw_data* folder.
* **problem**: This is the name of a registered problem that tensor2tensor needs. Detailed in the *generate_data* section below.
All paths should be from the root of the repo.
### Generate Data
This mode will download anExcerpt of 13,535 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:95be91626bbd648b, topic:dataset, readme:dataset, readme:datasets
matched fp:95be91626bbd648b, topic:tensorflow
matched fp:95be91626bbd648b, topic:transformer
matched fp:95be91626bbd648b, topic:chatbot, readme:chatbot