detoxify
rellm
| detoxify | rellm | |
|---|---|---|
| 4 | 7 | |
| 839 | 488 | |
| 1.9% | - | |
| 6.2 | 5.0 | |
| 23 days ago | 9 months ago | |
| Python | Python | |
| Apache License 2.0 | MIT License |
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.
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.
rellm
-
Run and create custom ChatGPT-like bots with OpenChat
- https://github.com/r2d4/rellm
-
Forcing GPT-4 or GPT-3.5-turbo to adhere to a specific output format
MS guidance as mentioned and ReLLM
- GitHub - r2d4/rellm: Exact structure out of any language model completion.
- AI Showdown: Wizard Vicuna vs. Stable Vicuna, GPT-4 as the judge (test in comments)
-
ReLLM: Exact Structure for Large Language Model Completions
There's probably a better API that wraps generate, but there's a bit more work than the logit mask.
You have to go one token at a time, otherwise the masking becomes combinatoric rather than linear (two tokens at a time -- need to generate all two token pairs, etc.).
But otherwise, that's what the code does! https://github.com/r2d4/rellm/blob/main/rellm/rellm.py#L21
- r2d4/rellm: Exact structure out of any language model completion.
What are some alternatives?
quickai - QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.
OpenChat - LLMs custom-chatbots console ⚡
kogpt - KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)
gpt-jargon - Jargon is a natural language programming language specified and executed by LLMs like GPT-4.
multi-label-sentiment-classifier - How to build a multi-label sentiment classifiers with Tez and PyTorch
convostack - Plug and play embeddable AI chatbot widget and backend deployment framework
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]
cedille-ai - ✒️ Cedille is a large French language model (6B), released under an open-source license
llama-api-server - A OpenAI API compatible REST server for llama.
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
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.