kogpt
detoxify
Our great sponsors
| kogpt | detoxify | |
|---|---|---|
| 1 | 4 | |
| 996 | 836 | |
| 0.5% | 4.3% | |
| 4.2 | 6.2 | |
| 3 months ago | 15 days ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | Apache License 2.0 |
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.
kogpt
detoxify
-
ML Discord Moderation Bot
I created a small discord moderation bot, src can be found at https://gist.github.com/KrautByte/975f404969f4de8f4147e1bb4f7b64cb using https://github.com/unitaryai/detoxify
- Cedille, the largest French language model , released in open source
-
Show HN: Cedille, the largest French language model, released in open source
Yeah, this kind of toxic output sadly still can happen :-/
We have fully analyzed the training dataset (1128 GB) using Detoxify (https://github.com/unitaryai/detoxify) to filter out problematic content. But of course detecting toxicity is a tough challenge in itself, so this process is imperfect at best.
We are using the RealToxicityPrompt framework (https://realtoxicityprompts.apps.allenai.org/) to analyse how toxic our models are and to steer our efforts in this direction. This means we are generating thousands of completions and analysing them to see how "nasty" the model is. We plan to write more on this topic soon.
But yeah, this is definitely far from being a solved problem, and our model (as well as all large language models) should be handled with care.
-
Implementing a toxicity detector in your chatbots
Detoxify is the result of three Kaggle competitions proposed to improve toxicity classifiers. Each had a different purpose within the toxicity classifiers context.
What are some alternatives?
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
quickai - QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.
Transformers4Rec - Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.
multi-label-sentiment-classifier - How to build a multi-label sentiment classifiers with Tez and PyTorch
kochat - Opensource Korean chatbot framework
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
zeroshot_topics - Topic Inference with Zeroshot models
cedille-ai - ✒️ Cedille is a large French language model (6B), released under an open-source license
aitg - plug and play many transformers models for http api or command line!
finetune-gpt2xl - Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed
kss - Kss: A Toolkit for Korean sentence segmentation
google-local-results-ai-server - A server code for serving BERT-based models for text classification. It is designed by SerpApi for heavy-load prototyping and production tasks, specifically for the implementation of the google-local-results-ai-parser gem.