🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

After two years with Poetry, Inseq just moved to Astral's new blazing fast package manager uv! Our CI installation step is now ~80% faster! 🔥 Congrats to Charlie Marsh and the team on the release, and godspeed for the cargo-like experience you are planning to build!

Wow!! This is great news🥳 Thanks Inseq! I’m excited to try it out!

Excited to present my recent work on Inseq and the #ICLR2024 PECoRe interpretability framework for the Sheffield NLP group this afternoon! Many thanks Cass Zhixue for inviting me! 🤗 🐛 Inseq: github.com/inseq-team/ins… 🐑🐑 PECoRe: openreview.net/forum?id=XTHfN…

🐑 PECoRe repository is now public (github.com/gsarti/pecore) and all model/datasets are available on Hugging Face (huggingface.co/collections/gs…)! 🐑Interested in using PECoRe on your models? Have a look at the Inseq implementation (`inseq attribute-context`)!

Want to learn how to detect and attribute context usage in LMs using Inseq? This Gradio demo using our CLI can teach you how! 🐛

Inseq v0.6 is out now on PyPI! 🔥 New CLI command for context attribution (Gabriele Sarti), new perturbation-based methods by Hosein Mohebbi & Cass Zhixue and optimizations incl. multi-gpu support! ⚡️ Huge shoutout to our contributors! ❤️ Release notes ⬇️ github.com/inseq-team/ins…

Today Inseq hit 300 ⭐️ on Github! A huge thank you to all our awesome users ❤️ Onwards to the next 300! 🤺

[1/4] Introducing “A Primer on the Inner Workings of Transformer-based Language Models”, a comprehensive survey on interpretability methods and the findings into the functioning of language models they have led to. ArXiv: arxiv.org/pdf/2405.00208

Today, we had the first seminar of our #XAI course! Gabriele Sarti presented the Inseq to interpret LMs and the PECORE framework to identify & attribute context dependence in LMs! 🚀🌟 Thank you, it was so interesting! 🤗 Great start to our series! gsarti.com/talk/polito-in…

The 🐑 PECoRe / 🌴 MIRAGE demo on Hugging Face Spaces is powered by our new attribute-context CLI command released in v0.6, and allows to export the code to reproduce your results locally with 🐛 Inseq. Check it out ➡️ hf.co/spaces/gsarti/…

🎓 We're thrilled to host Gabriele Sarti (Gabriele Sarti) in our PhD seminar series tomorrow, July 16th, from 12:00-13:00 in Oe67 BU 101! Join us for his talk on interpreting context usage in generative language models, featuring the Inseq toolkit and PECoRe framework. 🕛Don't miss it!

Thanks to the new treescope integration, Inseq now supports interactive visualizations for multidimensional attributions (show_granular), token highlights (show_tokens) and improved viz for attribute_context CLI! 🚀 Install main, will appear in v0.7 x.com/_ddjohnson/sta…

Very hyped for the new beautiful viz that just landed in the Inseq main branch! 🔥 This will empower users to explore attribution tensors more flexibly and intuitively. h/t to Daniel Johnson for his awesome work on the treescope toolkit powering this release!

Model Internals-based RAG Evaluation (MIRAGE) 🌴 is accepted to #EMNLP2024 Main! ➡️ To celebrate, here's our new MIRAGE demo combining Inseq and Transformers-specific LRP: huggingface.co/spaces/gsarti/…. Reach out if you want to catch up in Miami! 🤗🏖️