mutate
GODEL
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
mutate
GODEL
- Microsoft: Large-scale pretrained models for goal-directed dialog
-
Fine-tuning on Sales data?
I would use something like GODEL for something like this. https://github.com/microsoft/GODEL
- Godel: Large-Scale Pre-Training for Goal-Directed Dialog
-
Microsoft AI Researchers Open-Source 'GODEL': A Large Scale Pre-Trained Language Model For Dialog
Go to the github page here this is able to run on consumer hardware. The largest model they have need 2.7GB of memory. So running an instance will consume almost all the RAM in your GPU and you won't be able to use it for something else, but it will run on it.
-
"GODEL: Large-Scale Pre-Training for Goal-Directed Dialog", Peng et al 2022 {MS}
Github models to 2.7B: https://github.com/Microsoft/GODEL
What are some alternatives?
question_extractor - Generate question/answer training pairs out of raw text.
DialoGPT - Large-scale pretraining for dialogue
refinery - The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.
rasa - 💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Convoscope - AI tools to augment conversations on smart glasses, wearables, laptops, and smart meeting rooms.
tf-transformers - State of the art faster Transformer with Tensorflow 2.0 ( NLP, Computer Vision, Audio ).
DialogRPT - EMNLP 2020: "Dialogue Response Ranking Training with Large-Scale Human Feedback Data"
basaran - Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.
modular-diffusion - Python library for designing and training your own Diffusion Models with PyTorch.
TalkToModel - TalkToModel gives anyone with the powers of XAI through natural language conversations 💬!
forte - Forte is a flexible and powerful ML workflow builder. This is part of the CASL project: http://casl-project.ai/