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.
🦄 State-of-the-Art Conversational AI with Transfer Learning
| Date | Stars |
|---|---|
| 2026-07-24 | 1755 |
| 2026-07-25 | 1754 |
| 2026-07-28 | 1754 |
| 2026-07-30 | 1754 |
| 2026-07-31 | 1755 |
| 2026-08-06 | 1755 |
Today
— stars today
This week
+1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.06%/day
# 🦄 Building a State-of-the-Art Conversational AI with Transfer Learning The present repo contains the code accompanying the blog post [🦄 How to build a State-of-the-Art Conversational AI with Transfer Learning](https://medium.com/@Thomwolf/how-to-build-a-state-of-the-art-conversational-ai-with-transfer-learning-2d818ac26313). This code is a clean and commented code base with training and testing scripts that can be used to train a dialog agent leveraging transfer Learning from an OpenAI GPT and GPT-2 Transformer language model. This codebase can be used to reproduce the results of HuggingFace's participation to NeurIPS 2018 dialog competition [ConvAI2](http://convai.io/) which was state-of-the-art on the automatic metrics. The 3k+ lines of competition code was distilled in about 250 lines of training code with distributed & FP16 options to form the present repository. This model can be trained in about one hour on a 8 V100 cloud instance (currently costs about $25) and a pre-trained model is also made available. ## Installation To install and use the training and inference scripts please clone the repo and install the requirements: ```bash git clone https://github.com/huggingface/transfer-learning-conv-ai cd transfer-learning-conv-ai pip install -r requirements.txt python -m spacy download en ``` ## Installation with Docker To install using docker please build the self-contained image: ```bash docker build -t convai . ``` _Note: Make sure your Docker setup allocates enough memory to building the container. Building with the default of 1.75GB will fail due to large Pytorch wheel._ You can then enter the image ```bash ip-192-168-22-157:transfer-learning-conv-ai loretoparisi$ docker run --rm -it convai bash root@91e241bb823e:/# ls Dockerfile README.md boot dev home lib media models proc root sbin sys train.py utils.py LICENCE bin convai_evaluation.py etc interact.py lib64 mnt opt requirements.txt run srv tmp usr var ``` You can then run the `interact.py` script on the pretrained model: ```bash python3 interact.py --model models/ ``` ## Pretrained model We make a pretrained and fine-tuned model available on our S3 [here](https://s3.amazonaws.com/models.huggingface.co/transfer-learning-chatbot/finetuned_chatbot_gpt.tar.gz). The easiest way to download and use this model is just to run the `interact.py` script to talk with the model. Without any argument, this script will automatically download and cache our model. ## Using the training script The training script can be used in single GPU or multi GPU settings: ```bash python ./train.py # Single GPU training python -m torch.distributed.launch --nproc_per_node=8 ./train.py # Training on 8 GPUs ``` The training script accept several arguments to tweak the training: Argument | Type | Default value | Description ---------|------|---------------|------------ dataset_path | `str` | `""` | Path or url of the dataset. If empty download from S3. dataset_cache | `str` | `'./dataset_cache.bin'` | Path or url of the dataset cache model | `str` | `"openai-gpt"` | Path, url or short name of the model num_candidates | `int` | `2` | Number of candidates for training max_history | `int` | `2` | Number of previous exchanges to keep in history train_batch_size | `int` | `4` | Batch size for training valid_batch_size | `int` | `4` | Batch size for validation gradient_accumulation_steps | `int` | `8` | Accumulate gradients on several steps lr | `float` | `6.25e-5` | Learning rate lm_coef | `float` | `1.0` | LM loss coefficient mc_coef | `float` | `1.0` | Multiple-choice loss coefficient max_norm | `float` | `1.0` | Clipping gradient norm n_epochs | `int` | `3` | Number of training epochs personality_permutations | `int` | `1` | Number of permutations of personality sentences device | `str` | `"cuda" if torch.cuda.is_available() else "cpu"` | Device (cuda or cpu) fp16 | `str` | `""` | Set to O0,
Excerpt of 9,548 characters
Read on GitHub
Thomas Wolf · @huggingface
18
Sam Shleifer · United States
5
2
Julien Chaumond · @huggingface · United States
2
Loreto Parisi · @Musixmatchdev · Italy
2
1
1
1
1
Clem · @huggingface · United States
1
nicolas bertagnolli
1
Ganesh Krishnan · AiHello · Canada
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ecf43bf0b908542f, topic:deep-learning, topic:pytorch
matched fp:ecf43bf0b908542f, topic:gpt, readme:pretrained model
matched fp:ecf43bf0b908542f, topic:nlp