Scaling AI-based Data Processing with Hugging Face + Dask
•
23
Daniel van Strien PRO
davanstrien
AI & ML interests
Machine Learning Librarian
Articles
Organizations
davanstrien's activity
replied to
their
post
10 days ago
Thanks for the great video! Very nice that Binary Quantization works well too!
posted
an
update
10 days ago
Post
2364
Excited to see my weird
davanstrien/ufo-ColPali dataset featured in a video by
@sabrinaesaquino
!
The video covers using ColPali with Binary Quantization in Qdant to accelerate retrieval. 2x speed up with no performance drop in results 🛸
Video: https://youtu.be/_A90A-grwIc?si=oB3JAhJG8VQUZGLz
Blog post: https://danielvanstrien.xyz/posts/post-with-code/colpali-qdrant/2024-10-02_using_colpali_with_qdrant.html
The video covers using ColPali with Binary Quantization in Qdant to accelerate retrieval. 2x speed up with no performance drop in results 🛸
Video: https://youtu.be/_A90A-grwIc?si=oB3JAhJG8VQUZGLz
Blog post: https://danielvanstrien.xyz/posts/post-with-code/colpali-qdrant/2024-10-02_using_colpali_with_qdrant.html
-
- 2 replies
reacted to
malhajar's
post with ❤️
18 days ago
Post
3554
🇫🇷 Lancement officiel de l'OpenLLM French Leaderboard : initiative open-source pour référencer l’évaluation des LLMs francophones
Après beaucoup d’efforts et de sueurs avec Alexandre Lavallee, nous sommes ravis d’annoncer que le OpenLLMFrenchLeaderboard est en ligne sur Hugging Face (space url: le-leadboard/OpenLLMFrenchLeaderboard) la toute première plateforme dédiée à l’évaluation des grands modèles de langage (LLM) en français. 🇫🇷✨
Ce projet de longue haleine est avant tout une œuvre de passion mais surtout une nécessité absolue. Il devient urgent et vital d'oeuvrer à plus de transparence dans ce domaine stratégique des LLM dits multilingues. La première pièce à l'édifice est donc la mise en place d'une évaluation systématique et systémique des modèles actuels et futurs.
Votre modèle IA français est-il prêt à se démarquer ? Soumettez le dans notre espace, et voyez comment vous vous comparez par rapport aux autres modèles.
❓ Comment ça marche :
Soumettez votre LLM français pour évaluation, et nous le testerons sur des benchmarks de référence spécifiquement adaptés pour la langue française — notre suite de benchmarks comprend :
- BBH-fr : Raisonnement complexe
- IFEval-fr : Suivi d'instructions
- GPQA-fr : Connaissances avancées
- MUSR-fr : Raisonnement narratif
- MATH_LVL5-fr : Capacités mathématiques
- MMMLU-fr : Compréhension multitâche
Le processus est encore manuel, mais nous travaillons sur son automatisation, avec le soutien de la communauté Hugging Face.
@clem , on se prépare pour une mise à niveau de l’espace ? 😏👀
Ce n'est pas qu'une question de chiffres—il s'agit de créer une IA qui reflète vraiment notre langue, notre culture et nos valeurs. OpenLLMFrenchLeaderboard est notre contribution personnelle pour façonner l'avenir des LLM en France.
Après beaucoup d’efforts et de sueurs avec Alexandre Lavallee, nous sommes ravis d’annoncer que le OpenLLMFrenchLeaderboard est en ligne sur Hugging Face (space url: le-leadboard/OpenLLMFrenchLeaderboard) la toute première plateforme dédiée à l’évaluation des grands modèles de langage (LLM) en français. 🇫🇷✨
Ce projet de longue haleine est avant tout une œuvre de passion mais surtout une nécessité absolue. Il devient urgent et vital d'oeuvrer à plus de transparence dans ce domaine stratégique des LLM dits multilingues. La première pièce à l'édifice est donc la mise en place d'une évaluation systématique et systémique des modèles actuels et futurs.
Votre modèle IA français est-il prêt à se démarquer ? Soumettez le dans notre espace, et voyez comment vous vous comparez par rapport aux autres modèles.
❓ Comment ça marche :
Soumettez votre LLM français pour évaluation, et nous le testerons sur des benchmarks de référence spécifiquement adaptés pour la langue française — notre suite de benchmarks comprend :
- BBH-fr : Raisonnement complexe
- IFEval-fr : Suivi d'instructions
- GPQA-fr : Connaissances avancées
- MUSR-fr : Raisonnement narratif
- MATH_LVL5-fr : Capacités mathématiques
- MMMLU-fr : Compréhension multitâche
Le processus est encore manuel, mais nous travaillons sur son automatisation, avec le soutien de la communauté Hugging Face.
@clem , on se prépare pour une mise à niveau de l’espace ? 😏👀
Ce n'est pas qu'une question de chiffres—il s'agit de créer une IA qui reflète vraiment notre langue, notre culture et nos valeurs. OpenLLMFrenchLeaderboard est notre contribution personnelle pour façonner l'avenir des LLM en France.
- 1 reply
posted
an
update
about 1 month ago
Post
1145
ColPali is an exciting new approach to multimodal document retrieval, but some doubt its practical use with existing vector DBs.
It turns out it's super easy to use Qdrant to index and search ColPali embeddings efficiently.
Blog post here: https://danielvanstrien.xyz/posts/post-with-code/colpali-qdrant/2024-10-02_using_colpali_with_qdrant.html
Very silly demo: davanstrien/ufo-ColPali-Search
It turns out it's super easy to use Qdrant to index and search ColPali embeddings efficiently.
Blog post here: https://danielvanstrien.xyz/posts/post-with-code/colpali-qdrant/2024-10-02_using_colpali_with_qdrant.html
Very silly demo: davanstrien/ufo-ColPali-Search
reacted to
jsulz's
post with 🚀
about 1 month ago
Post
1796
In August, the XetHub team joined Hugging Face
- https://huggingface.co/blog/xethub-joins-hf - and we’ve been rolling up our sleeves to bring the best of both worlds together. We started with a deep dive into the current state of files stored with Git LFS on the Hub.
Getting this information was no small feat. We had to:
* Analyze a complete database dump of all repositories and files stored in Git LFS across Hugging Face.
* Parse through metadata on file sizes and types to accurately map the storage breakdown across Spaces, Models, and Datasets.
You can read more about the findings (with some jaw-dropping stats + charts) here https://www.linkedin.com/feed/update/urn:li:activity:7244486280351285248
- https://huggingface.co/blog/xethub-joins-hf - and we’ve been rolling up our sleeves to bring the best of both worlds together. We started with a deep dive into the current state of files stored with Git LFS on the Hub.
Getting this information was no small feat. We had to:
* Analyze a complete database dump of all repositories and files stored in Git LFS across Hugging Face.
* Parse through metadata on file sizes and types to accurately map the storage breakdown across Spaces, Models, and Datasets.
You can read more about the findings (with some jaw-dropping stats + charts) here https://www.linkedin.com/feed/update/urn:li:activity:7244486280351285248
reacted to
asoria's
post with 👍
about 1 month ago
Post
2326
📝 I wrote a tutorial on how to get started with the fine-tuning process using Hugging Face tools, providing an end-to-end workflow.
The tutorial covers creating a new dataset using the new SQL Console 🛢 and fine-tuning a model with SFT, guided by the Notebook Creator App 📙.
👉 You can read the full article here:
https://huggingface.co/blog/asoria/easy-fine-tuning-with-hf
asoria/auto-notebook-creator
The tutorial covers creating a new dataset using the new SQL Console 🛢 and fine-tuning a model with SFT, guided by the Notebook Creator App 📙.
👉 You can read the full article here:
https://huggingface.co/blog/asoria/easy-fine-tuning-with-hf
asoria/auto-notebook-creator
reacted to
m-ric's
post with 🔥
about 1 month ago
Post
3204
🌎 𝐓𝐡𝐞 𝐟𝐢𝐫𝐬𝐭 𝐞𝐯𝐞𝐫 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧 𝐰𝐞𝐚𝐭𝐡𝐞𝐫 𝐦𝐨𝐝𝐞𝐥: 𝐏𝐫𝐢𝐭𝐡𝐯𝐢 𝐖𝐱𝐂 𝐞𝐧𝐚𝐛𝐥𝐞𝐬 𝐥𝐢𝐟𝐞-𝐬𝐚𝐯𝐢𝐧𝐠 𝐰𝐞𝐚𝐭𝐡𝐞𝐫 𝐩𝐫𝐞𝐝𝐢𝐜𝐭𝐢𝐨𝐧𝐬
Hurricane Katrina killed hundreds of people as it made landfall on New Orleans in 2005 - many of these deaths could have been avoided if alerts had been given one day earlier. Accurate weather forecasts are really life-saving.
🔥 Now, NASA and IBM just dropped a game-changing new model: the first ever foundation model for weather! This means, it's the first time we have a generalist model not restricted to one task, but able to predict 160 weather variables!
Prithvi WxC (Prithvi, “पृथ्वी”, is the Sanskrit name for Earth) - is a 2.3 billion parameter model, with an architecture close to previous vision transformers like Hiera.
💡 But it comes with some important tweaks: under the hood, Prithvi WxC uses a clever transformer-based architecture with 25 encoder and 5 decoder blocks. It alternates between "local" and "global" attention to capture both regional and global weather patterns.
𝗞𝗲𝘆 𝗶𝗻𝘀𝗶𝗴𝗵𝘁𝘀:
🔮 Nails short-term forecasts - Prithvi WxC crushed it on 6-12 hour predictions, even outperforming some traditional numerical weather models
🌀 Tracks hurricanes like a champ - For Hurricane Ida, it predicted the landfall location within 5 km (vs 20+ km errors from other AI models), which is a huge progress!
🔍 6x downscaling power - Can zoom in on weather data to 6x higher resolution with 4x lower error than basic methods
🌊 Models elusive gravity waves - Accurately simulates these crucial but hard-to-capture atmospheric oscillations
As climate change intensifies, tools like Prithvi WxC will become more and more crucial to avoid disasters!
Announcement post 👉 https://newsroom.ibm.com/2024-09-23-ibm-and-nasa-release-open-source-ai-model-on-hugging-face-for-weather-and-climate-applications
Model on the Hub 👉 https://huggingface.co/Prithvi-WxC
Thank you @clem for highlighting it!
Hurricane Katrina killed hundreds of people as it made landfall on New Orleans in 2005 - many of these deaths could have been avoided if alerts had been given one day earlier. Accurate weather forecasts are really life-saving.
🔥 Now, NASA and IBM just dropped a game-changing new model: the first ever foundation model for weather! This means, it's the first time we have a generalist model not restricted to one task, but able to predict 160 weather variables!
Prithvi WxC (Prithvi, “पृथ्वी”, is the Sanskrit name for Earth) - is a 2.3 billion parameter model, with an architecture close to previous vision transformers like Hiera.
💡 But it comes with some important tweaks: under the hood, Prithvi WxC uses a clever transformer-based architecture with 25 encoder and 5 decoder blocks. It alternates between "local" and "global" attention to capture both regional and global weather patterns.
𝗞𝗲𝘆 𝗶𝗻𝘀𝗶𝗴𝗵𝘁𝘀:
🔮 Nails short-term forecasts - Prithvi WxC crushed it on 6-12 hour predictions, even outperforming some traditional numerical weather models
🌀 Tracks hurricanes like a champ - For Hurricane Ida, it predicted the landfall location within 5 km (vs 20+ km errors from other AI models), which is a huge progress!
🔍 6x downscaling power - Can zoom in on weather data to 6x higher resolution with 4x lower error than basic methods
🌊 Models elusive gravity waves - Accurately simulates these crucial but hard-to-capture atmospheric oscillations
As climate change intensifies, tools like Prithvi WxC will become more and more crucial to avoid disasters!
Announcement post 👉 https://newsroom.ibm.com/2024-09-23-ibm-and-nasa-release-open-source-ai-model-on-hugging-face-for-weather-and-climate-applications
Model on the Hub 👉 https://huggingface.co/Prithvi-WxC
Thank you @clem for highlighting it!
reacted to
fdaudens's
post with 🚀🔥
about 1 month ago
Post
3271
A big day for multimodal models!
Llama 3.2 is out with a major update: it can now process images.
Key highlights:
• 11B and 90B vision models
• Small 1B and 3B text models for mobile devices
Eval results already on the leaderboard: open-llm-leaderboard/open_llm_leaderboard
Collection: meta-llama/llama-32-66f448ffc8c32f949b04c8cf
Llama 3.2 is out with a major update: it can now process images.
Key highlights:
• 11B and 90B vision models
• Small 1B and 3B text models for mobile devices
Eval results already on the leaderboard: open-llm-leaderboard/open_llm_leaderboard
Collection: meta-llama/llama-32-66f448ffc8c32f949b04c8cf
- 1 reply
reacted to
fdaudens's
post with 🔥
about 1 month ago
Post
1782
Exciting news in AI: Molmo, a groundbreaking family of open-source multimodal models, has just been announced! 🚀
Key points:
- Closes the gap with proprietary systems on benchmarks & human evals
- Trained on high-quality data (< 1M image-text pairs vs billions)
- Introduces pointing capability for rich interactions
- Fully open weights, data, and training code
The 72B model outperforms several proprietary systems, while the 1B model nearly matches GPT-4V. Small is indeed the new big in AI!
There's an interactive demo available using Molmo-7B-D. Definitely worth checking out to see its capabilities firsthand.
All model weights, data, and code will be released soon. This is a significant step towards truly open, cutting-edge multimodal AI.
The future of AI research and applications is looking brighter than ever! 🤖🖼️
👉 Demo: https://molmo.allenai.org/
👉 Models: allenai/molmo-66f379e6fe3b8ef090a8ca19
#AI #MachineLearning #OpenSource #ComputerVision
Key points:
- Closes the gap with proprietary systems on benchmarks & human evals
- Trained on high-quality data (< 1M image-text pairs vs billions)
- Introduces pointing capability for rich interactions
- Fully open weights, data, and training code
The 72B model outperforms several proprietary systems, while the 1B model nearly matches GPT-4V. Small is indeed the new big in AI!
There's an interactive demo available using Molmo-7B-D. Definitely worth checking out to see its capabilities firsthand.
All model weights, data, and code will be released soon. This is a significant step towards truly open, cutting-edge multimodal AI.
The future of AI research and applications is looking brighter than ever! 🤖🖼️
👉 Demo: https://molmo.allenai.org/
👉 Models: allenai/molmo-66f379e6fe3b8ef090a8ca19
#AI #MachineLearning #OpenSource #ComputerVision
posted
an
update
about 2 months ago
Post
2177
Yesterday, I shared a blog post on generating data for fine-tuning ColPali using the
Qwen/Qwen2-VL-7B-Instruct model.
To simplify testing this approach, I created a Space that lets you generate queries from an input document page image: davanstrien/ColPali-Query-Generator
I think there is much room for improvement, but I'm excited about the potential for relatively small VLMs to create synthetic data.
You can read the original blog post that goes into more detail here: https://danielvanstrien.xyz/posts/post-with-code/colpali/2024-09-23-generate_colpali_dataset.html
To simplify testing this approach, I created a Space that lets you generate queries from an input document page image: davanstrien/ColPali-Query-Generator
I think there is much room for improvement, but I'm excited about the potential for relatively small VLMs to create synthetic data.
You can read the original blog post that goes into more detail here: https://danielvanstrien.xyz/posts/post-with-code/colpali/2024-09-23-generate_colpali_dataset.html
reacted to
pain's
post with ❤️
about 2 months ago
Post
2418
We have published an excellent paper for Arabic CLIP model.
Paper link:
https://aclanthology.org/2024.arabicnlp-1.9/
More information in this website:
https://arabic-clip.github.io/Arabic-CLIP/
All datasets, models, and demo are published to Huggingface:
https://huggingface.co/Arabic-Clip
The codes are published to github:
https://github.com/Arabic-Clip/Arabic-CLIP
Paper link:
https://aclanthology.org/2024.arabicnlp-1.9/
More information in this website:
https://arabic-clip.github.io/Arabic-CLIP/
All datasets, models, and demo are published to Huggingface:
https://huggingface.co/Arabic-Clip
The codes are published to github:
https://github.com/Arabic-Clip/Arabic-CLIP
- 1 reply
posted
an
update
about 2 months ago
Post
3118
ColPali is revolutionizing multimodal retrieval, but could it be even more effective with domain-specific fine-tuning?
Check out my latest blog post, where I guide you through creating a ColPali fine-tuning dataset using Qwen/Qwen2-VL-7B-Instruct to generate queries for a collection of UFO documents sourced from the Internet Archive.
The post covers:
- Introduction to data for ColPali models
- Using Qwen2-VL for retrieval query generation
- Tips for better query generation
Check out the post here:
https://danielvanstrien.xyz/posts/post-with-code/colpali/2024-09-23-generate_colpali_dataset.html
The resulting Hugging Face dataset: davanstrien/ufo-ColPali
Check out my latest blog post, where I guide you through creating a ColPali fine-tuning dataset using Qwen/Qwen2-VL-7B-Instruct to generate queries for a collection of UFO documents sourced from the Internet Archive.
The post covers:
- Introduction to data for ColPali models
- Using Qwen2-VL for retrieval query generation
- Tips for better query generation
Check out the post here:
https://danielvanstrien.xyz/posts/post-with-code/colpali/2024-09-23-generate_colpali_dataset.html
The resulting Hugging Face dataset: davanstrien/ufo-ColPali
- 1 reply
reacted to
MoritzLaurer's
post with 👀
about 2 months ago
Post
1889
The new NIM Serverless API by HF and Nvidia is a great option if you want a reliable API for open-weight LLMs like Llama-3.1-405B that are too expensive to run on your own hardware.
- It's pay-as-you-go, so it doesn't have rate limits like the standard HF Serverless API and you don't need to commit to hardware like for a dedicated endpoint.
- It works out-of-the box with the new v0.25 release of our huggingface_hub.InferenceClient
- It's specifically tailored to a small collection of popular open-weight models. For a broader selection of open models, we recommend using the standard HF Serverless API.
- Note that you need a token from an Enterprise Hub organization to use it.
Details in this blog post: https://huggingface.co/blog/inference-dgx-cloud
Compatible models in this HF collection: nvidia/nim-serverless-inference-api-66a3c6fcdcb5bbc6e975b508
Release notes with many more features of huggingface_hub==0.25.0: https://github.com/huggingface/huggingface_hub/releases/tag/v0.25.0
Copy-pasteable code in the first comment:
- It's pay-as-you-go, so it doesn't have rate limits like the standard HF Serverless API and you don't need to commit to hardware like for a dedicated endpoint.
- It works out-of-the box with the new v0.25 release of our huggingface_hub.InferenceClient
- It's specifically tailored to a small collection of popular open-weight models. For a broader selection of open models, we recommend using the standard HF Serverless API.
- Note that you need a token from an Enterprise Hub organization to use it.
Details in this blog post: https://huggingface.co/blog/inference-dgx-cloud
Compatible models in this HF collection: nvidia/nim-serverless-inference-api-66a3c6fcdcb5bbc6e975b508
Release notes with many more features of huggingface_hub==0.25.0: https://github.com/huggingface/huggingface_hub/releases/tag/v0.25.0
Copy-pasteable code in the first comment:
-
- 2 replies
replied to
MoritzLaurer's
post
about 2 months ago
Very exciting to see this! I often want to use an LLM for a short period, and setting up a whole endpoint for this can be overkill. This seems like a very neat solution!
Do you think there is a chance that any VLMs will be added soon!?
posted
an
update
about 2 months ago
Post
446
🛸 I'm working on a pipeline for creating domain-specific ColPali fine-tuning datasets using a collection of UFO newsletters from the Internet Archive as a case study.
I will have a full notebook to share on Monday, but you can already take a look at the dataset here: davanstrien/ufo-ColPali
I will have a full notebook to share on Monday, but you can already take a look at the dataset here: davanstrien/ufo-ColPali
reacted to
albertvillanova's
post with ❤️👍
about 2 months ago
Post
1503
Check out the new Structured #Wikipedia dataset by Wikimedia Enterprise: abstract, infobox, structured sections, main image,...
Currently in early beta (English & French). Explore it and give feedback: wikimedia/structured-wikipedia
More info: https://enterprise.wikimedia.com/blog/hugging-face-dataset/
@sdelbecque @resquito-wmf
Currently in early beta (English & French). Explore it and give feedback: wikimedia/structured-wikipedia
More info: https://enterprise.wikimedia.com/blog/hugging-face-dataset/
@sdelbecque @resquito-wmf
posted
an
update
about 2 months ago
Post
1687
Almost ready: search for a Hugging Face dataset on the Hub from information in the datasets viewer preview!
Soon, you can find deep-cut datasets even if they don't have a full dataset card (you should still document your datasets!)
You can help improve this project by rating synthetic user search queries for hub datasets.
If you have a Hub login, you can start annotating in Argilla
in < 5 seconds here: https://davanstrien-my-argilla.hf.space/dataset/1100a091-7f3f-4a6e-ad51-4e859abab58f/annotation-mode
I need to do some tidying, but I'll share all the code and in-progress datasets for this soon!
Soon, you can find deep-cut datasets even if they don't have a full dataset card (you should still document your datasets!)
You can help improve this project by rating synthetic user search queries for hub datasets.
If you have a Hub login, you can start annotating in Argilla
in < 5 seconds here: https://davanstrien-my-argilla.hf.space/dataset/1100a091-7f3f-4a6e-ad51-4e859abab58f/annotation-mode
I need to do some tidying, but I'll share all the code and in-progress datasets for this soon!
posted
an
update
2 months ago
Post
1499
The Hugging Face Semantic Dataset Search Space is back in action! You can find similar datasets by ID or perform a semantic search of dataset cards.
Give it a try: librarian-bots/huggingface-datasets-semantic-search
Give it a try: librarian-bots/huggingface-datasets-semantic-search
- 1 reply