scadsai-german-llm (ScaDS.AI German LLM)

cschroeder

posted an update 8 days ago

Post

330

💡𝗟𝗼𝗼𝗸𝗶𝗻𝗴 𝗳𝗼𝗿 𝘀𝘂𝗽𝗽𝗼𝗿𝘁: 𝗛𝗮𝘃𝗲 𝘆𝗼𝘂 𝗲𝘃𝗲𝗿 𝗵𝗮𝗱 𝘁𝗼 𝗼𝘃𝗲𝗿𝗰𝗼𝗺𝗲 𝗮 𝗹𝗮𝗰𝗸 𝗼𝗳 𝗹𝗮𝗯𝗲𝗹𝗲𝗱 𝗱𝗮𝘁𝗮 𝘁𝗼 𝗱𝗲𝗮𝗹 𝘄𝗶𝘁𝗵 𝗮𝗻 𝗡𝗟𝗣 𝘁𝗮𝘀𝗸?

Are you working on Natural Language Processing tasks and have faced the challenge of a lack of labeled data before? 𝗪𝗲 𝗮𝗿𝗲 𝗰𝘂𝗿𝗿𝗲𝗻𝘁𝗹𝘆 𝗰𝗼𝗻𝗱𝘂𝗰𝘁𝗶𝗻𝗴 𝗮 𝘀𝘂𝗿𝘃𝗲𝘆 to explore the strategies used to address this bottleneck, especially in the context of recent advancements, including but not limited to large language models.

The survey is non-commercial and conducted solely for academic research purposes. The results will contribute to an open-access publication that also benefits the community.

👉 With only 5–15 minutes of your time, you would greatly help to investigate which strategies are used by the #NLP community to overcome a lack of labeled data.

❤️How you can help even more: If you know others working on supervised learning and NLP, please share this survey with them—we’d really appreciate it!

Survey: https://bildungsportal.sachsen.de/umfragen/limesurvey/index.php/538271
Estimated time required: 5–15 minutes
Deadline for participation: January 12, 2025

#NLP #ML

stefan-it

posted an update 16 days ago

Post

1127

My latest project is the outcome of the last 2+ years working with TPUs from the amazing TPU Research Cloud (TRC) program and training Encoder-only LMs with the TensorFlow Model Garden library.

👉 Link: https://github.com/stefan-it/model-garden-lms

An overview of some features:

- Cheatsheet for setting-up a TPU VM Pod (with all necessary dependencies) to pretrain LMs with TF Model Garden
- Conversion scripts that convert TF Model Garden weights to Hugging Face Transformers-compatible models
- Supported architectures include BERT, BERT with Token Dropping and TEAMS

I also released BERT-based models pretrained on the great Hugging Face FineWeb and FineWeb-Edu datasets (10BT subset). With more to come!

👉 Model Hub Link: https://huggingface.co/model-garden-lms

If you find these resources useful, please give them a like!

Made from Bavarian Oberland with ❤️ and 🥨.

christopher

posted an update 17 days ago

Post

1562

The folks at Foursquare released a dataset of 104.5 million places of interest ( foursquare/fsq-os-places) and here's all of them on a plot

3 replies

·

christopher

posted an update 19 days ago

Post

2313

The Lichess database of games, puzzles, and engine evaluations is now on the Hub: https://huggingface.co/Lichess

Billions of chess data points to download, query, and stream and we're excited to see what you'll build with it! ♟️ 🤗

- Lichess/positions-datasets-66f50837db5cd3287d60d489
- Lichess/games-datasets-66f508df78f4b43e1bb2d353

cschroeder

posted an update about 1 month ago

Post

1082

🐣 New release: small-text v2.0.0.dev1

With small language models on the rise, the new version of small-text has been long overdue! Despite the generative AI hype, many real-world tasks still rely on supervised learning—which is reliant on labeled data.

Highlights:
- Four new query strategies: Try even more combinations than before.
- Vector indices integration: HNSW and KNN indices are now available via a unified interface and can easily be used within your code.
- Simplified installation: We dropped the torchtext dependency and cleaned up a lot of interfaces.

Github: https://github.com/webis-de/small-text

👂 Try it out for yourself! We are eager to hear your feedback.
🔧 Share your small-text applications and experiments in the newly added showcase section.
🌟 Support the project by leaving a star on the repo!

#activelearning #nlproc #machinelearning

cschroeder

posted an update about 1 month ago

Post

695

#EMNLP2024 is happening soon! Unfortunately, I will not be on site, but I will present our poster virtually on Wednesday, Nov 13 (7:45 EST / 13:45 CEST) in Virtual Poster Session 2.

In this work, we leverage self-training in an active learning loop in order to train small language models with even less data. Hope to see you there!

1 reply

·

cschroeder

posted an update 4 months ago

Post

401

⚖️ 𝐀𝐈 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐢𝐬 𝐂𝐨𝐩𝐲𝐫𝐢𝐠𝐡𝐭 𝐈𝐧𝐟𝐫𝐢𝐧𝐠𝐞𝐦𝐞𝐧𝐭

This bold claim is not my opinion, but it has been made in a recent "report" of a group, whose stance is recognizable in their name. It is roughly translated as "Authors' Rights Initiative". They published a report which was also presented before the EU Parliament according to the LinkedIn post below.

I am not really interested in politics, but as an EU citizen I am of course somewhat interested in a reasonable and practical version of the EU AI Act. Not saying there should not be rules around data and AI, but this report is obviously very biased towards one side.

While I think the report itself does not deserve attention, I post it in the hope that you find more examples, where they did not address the issue adequately. Feel free to add to my LinkedIn posts (where the original authors will see it) or here.

[en] Executive summary: https://urheber.info/media/pages/diskurs/ai-training-is-copyright-infringement/3b900058e6-1725460935/executive-summary_engl_final_29-08-2024.pdf
[de] Full report: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4946214

LinkedIn: https://www.linkedin.com/posts/activity-7238912869268959232-6cFx

christopher

posted an update 4 months ago

Post

1323

4 million chess puzzles

cschroeder

posted an update 4 months ago

Post

684

🌟 Liger Kernel: Efficient Triton Kernels for LLM Training

LIGER "is a [Hugging Face-compatible] collection of Triton kernels designed specifically for LLM training. It can effectively increase multi-GPU training throughput by 20% and reduces memory usage by 60%."

GitHub: https://github.com/linkedin/Liger-Kernel

cschroeder

posted an update 4 months ago

Post

346

📄 ACL 2024: The Missing Papers

Apparently, some papers from the ACL 2024 are still not listed in the ACL Anthology. While this issue will hopefully be fixed soon, we should give those papers additional spotlight.

Some of my favorites:

1. Dolma is an English corpus that encompasses 3 trillion tokens. Additionally, it is accompanied by an exceptional software package that consdierably advances the state-of-the-art in preparing data for LLM pretraining. (Source: I am currently using Dolma.)
Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research (2402.00159)

2. In the paper "Same Task, More Tokens: the Impact of Input Length on
the Reasoning Performance of Large Language Models", the authors show how extending the context length impacts an LLM's reasoning performance. I asked myself a similar question a few months ago, and therefore this paper is highly interesting to me.
Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models (2402.14848)

This was brought to my attention through a Linkedin post by @ShayeghB , who is also affected:
Ensemble-Based Unsupervised Discontinuous Constituency Parsing by Tree Averaging (2403.00143)

View all the missing papers here:
https://theshayegh.github.io/ACL2024MissingPapers/