giskard
awesome-ai-safety
giskard | awesome-ai-safety | |
---|---|---|
7 | 5 | |
3,164 | 138 | |
12.9% | 8.0% | |
10.0 | 5.6 | |
8 days ago | 7 months ago | |
Python | ||
Apache License 2.0 | 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.
giskard
- Show HN: Evaluate LLM-based RAG Applications with automated test set generation
-
Why is it so important to evaluate Large Language Models (LLMs)? 🤯🔥
Unchecked biases in LLMs can inadvertently perpetuate harmful stereotypes or produce misleading information, which in turn can produce severe consequences. In this article, we'll demonstrate how to evaluate your LLMs using an open source model testing framework, Giskard. 🤓
- The testing framework dedicated to ML models, from tabular to LLMs
-
Show HN: Python library to scan ML models for vulnerabilities
Hi! I’ve been working on this automatic scanner for ML models to detect issues like underperforming data slices, overconfidence in predictions, robustness problems, and others. It supports all main Python ML frameworks (sklearn, torch, xgboost, …) and integrates with the quality assurance solution we are building at Giskard AI (https://giskard.ai) to systematically test models before putting them in production.
It is still a beta and I would love to hear your feedback if you have the time to try it out.
We have quite a few tutorials in the docs with ready-made colab notebooks to make it easy to get started.
If you are interested in the code:
https://github.com/Giskard-AI/giskard/tree/main/python-clien...
-
[P] Open-source solution to scan AI models for vulnerabilities
Sure! Benjamini-Hochberg is a very good recommendation, much simpler than the alpha investing procedures I mentioned which makes it easily to implement in our case. I will give it a try, if there’s an easy way to set this up it could be included in some of the next releases. I’ll let you know. FYI, I added this to our issue tracker.
-
[R] LMFlow Benchmark: An Automatic Evaluation Framework for Open-Source LLMs
This is super interesting! Thanks for sharing. We're also working on this research field from an open-source angle (https://github.com/Giskard-AI/giskard)
-
How are you testing your ML Systems?
Code repository: https://github.com/Giskard-AI/giskard
awesome-ai-safety
-
Ask HN: Who is hiring? (October 2023)
Giskard - Testing framework for ML models| Multiple roles | Full-time | France | https://giskard.ai/
We are building the first collaborative & open-source Quality Assurance platform for all ML models - including Large Language Models.
Founded in 2021 in Paris by ex-Dataiku engineers, we are an emerging player in the fast-growing market of AI Quality & Safety.
Giskard helps Data Scientists & ML Engineering teams collaborate to evaluate, test & monitor AI models. We help organizations increase the efficiency of their AI development workflow, eliminate risks of AI biases and ensure robust, reliable & ethical AI models. Our open-source platform is used by dozens of ML teams across industries, both at enterprise companies & startups.
In 2022, we raised our first round of 1.5 million euros, led by Elaia, with participation from Bessemer and notable angel investors including the CTO of Hugging Face. To read more about this fundraising and how it will accelerate our growth, you can read this announcement: https://www.giskard.ai/knowledge/news-fundraising-2022
In 2023, we received a strategic investment from the European Commission to build a SaaS platform to automate compliance with the upcoming EU AI regulation. You can read more here: https://www.giskard.ai/knowledge/1-000-github-stars-3meu-and...
We are assembling a team of champions: Software Engineers, Machine Learning researchers, and Data Scientists ; to build our AI Quality platform and expand it to new types of AI models and industries. We have a culture of continuous learning & quality, and we help each other achieve high standards & goals!
We aim to grow from 15 to 25 people in the next 12 months. We're hiring the following roles:
-
Ask HN: Who is hiring? (August 2023)
Giskard - Testing framework for ML models| Multiple roles | Full-time | France | https://giskard.ai/
We are building the first collaborative & open-source Quality Assurance platform for all ML models - including Large Language Models.
Founded in 2021 in Paris by ex-Dataiku engineers, we are an emerging player in the fast-growing market of AI Safety & Security.
Giskard helps Data Scientists & ML Engineering teams collaborate to evaluate, test & monitor AI models. We help organizations increase the efficiency of their AI development workflow, eliminate risks of AI biases and ensure robust, reliable & ethical AI models. Our open-source platform is used by dozens of ML teams across industries, both at enterprise companies & startups.
In 2022, we raised our first round of 1.5 million euros, led by Elaia, with participation from Bessemer and notable angel investors including the CTO of Hugging Face. To read more about this fundraising and how it will accelerate our growth, you can read this announcement: https://www.giskard.ai/knowledge/news-fundraising-2022
In 2023, we received a strategic investment from the European Commission to build a SaaS platform to automate compliance with the upcoming EU AI regulation. You can read more here: https://www.giskard.ai/knowledge/1-000-github-stars-3meu-and...
We are assembling a team of champions: Software Engineers, Machine Learning researchers, and Data Scientists ; to build our AI Quality platform and expand it to new types of AI models and industries. We have a culture of continuous learning & quality, and we help each other achieve high standards & goals!
We aim to grow from 15 to 25 people in the next 12 months. We're hiring the following roles:
* Software Engineer - https://apply.workable.com/giskard/j/AD2C90B581/ (Python, Java, Typescript, Vue.js, Cloud skills)
* Machine Learning Researcher - https://apply.workable.com/giskard/j/E89FE8E310/ (post-PhD)
* Data Science lead - https://apply.workable.com/giskard/j/E89FE8E310/ (ML + consulting experience required)
* Growth marketing intern - https://apply.workable.com/giskard/j/C8635E9B0C/
* Data Science intern - https://apply.workable.com/giskard/j/7F0B341852/
-
Show HN: Python library to scan ML models for vulnerabilities
Hi! I’ve been working on this automatic scanner for ML models to detect issues like underperforming data slices, overconfidence in predictions, robustness problems, and others. It supports all main Python ML frameworks (sklearn, torch, xgboost, …) and integrates with the quality assurance solution we are building at Giskard AI (https://giskard.ai) to systematically test models before putting them in production.
It is still a beta and I would love to hear your feedback if you have the time to try it out.
We have quite a few tutorials in the docs with ready-made colab notebooks to make it easy to get started.
If you are interested in the code:
https://github.com/Giskard-AI/giskard/tree/main/python-clien...
-
[R] Awesome AI Safety – A curated list of papers & technical articles on AI Quality & Safety
Repository: https://github.com/Giskard-AI/awesome-ai-safety
- AI Safety – curated papers for safer, ethical, and reliable AI
What are some alternatives?
deepchecks - Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.
opentofu - OpenTofu lets you declaratively manage your cloud infrastructure.
metaflow - :rocket: Build and manage real-life ML, AI, and data science projects with ease!
tabby - Self-hosted AI coding assistant
PyBeam-QA - An simple GUI program for performing radiotherapy QA
awesome-langchain - 😎 Awesome list of tools and projects with the awesome LangChain framework
LMFlow - An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
refact - WebUI for Fine-Tuning and Self-hosting of Open-Source Large Language Models for Coding
MindsDB - The platform for customizing AI from enterprise data
nl-wallet - NL Public Reference Wallet
lm-evaluation-harness - A framework for few-shot evaluation of language models.
mentat - Mentat - The AI Coding Assistant