Hugging Face's logo
David Berenstein's picture
89 125 315

David Berenstein

davidberenstein1957
cswiz's profile picture jcrubino2's profile picture hatted's profile picture
ยท

AI & ML interests

None yet

Recent Activity

liked a model 10 minutes ago
Qwen/Qwen3-0.6B
commented on their article about 1 hour ago
Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs
posted an update about 24 hours ago
Good answers are not necessarily factual answers: an analysis of hallucination in leading LLMs https://huggingface.co/blog/davidberenstein1957/phare-analysis-of-hallucination-in-leading-llms
View all activity

Organizations

Giskard's profile picture SomosNLP's profile picture Blog-explorers's profile picture Pruna AI's profile picture Social Post Explorers's profile picture Dataset Viber's profile picture Data Is Better Together Contributor's profile picture Model Context Protocol - MCP servers's profile picture Reasoning datasets competition 's profile picture

davidberenstein1957's activity

posted an update about 24 hours ago
posted an update 15 days ago
posted an update 20 days ago
posted an update 22 days ago
view post
Post
1382
RealHarm: A Collection of Real-World Language Model Application Failure

I'm David from Giskard, and we work on securing your Agents.
Today, we are launching RealHarm: a dataset of real-world problematic interactions with AI agents, drawn from publicly reported incidents.

Check out the dataset and paper: https://realharm.giskard.ai/
posted an update about 1 month ago
view post
Post
2090
๐Ÿšจ New Bonus Unit: Tracing & Evaluating Your Agent! ๐Ÿšจ

Learn how to transform your agent from a simple demo into a robust, reliable product ready for real users.

UNIT: https://huggingface.co/learn/agents-course/bonus-unit2/introduction

In this unit, you'll learn:
- Offline Evaluation โ€“ Benchmark and iterate your agent using datasets.
- Online Evaluation โ€“ Continuously track key metrics such as latency, costs, and user feedback.

Happy testing and improving!

Thanks Langfuse team!
posted an update 2 months ago
reacted to their post with ๐Ÿš€๐Ÿ”ฅ 2 months ago
view post
Post
4247
๐ŸฅŠ Epic Agent Framework Showdown! Available today!

๐Ÿ”ต In the blue corner, the versatile challenger with a proven track record of knowledge retrieval: LlamaIndex!

๐Ÿ›‘ In the red corner, the defender, weighing in with lightweight efficiency: Hugging Face smolagents!

๐Ÿ”— URL: agents-course

We just published the LlamaIndex unit for the agents course, and it is set to offer a great contrast between the smolagents unit by looking at

- What makes llama-index stand-out
- How the LlamaHub is used for integrations
- Creating QueryEngine components
- Using agents and tools
- Agentic and multi-agent workflows

The team has been working flat-out on this for a few weeks. Supported by Logan Markewich and Laurie Voss over at LlamaIndex.

Who won? You decide!
posted an update 2 months ago
view post
Post
4247
๐ŸฅŠ Epic Agent Framework Showdown! Available today!

๐Ÿ”ต In the blue corner, the versatile challenger with a proven track record of knowledge retrieval: LlamaIndex!

๐Ÿ›‘ In the red corner, the defender, weighing in with lightweight efficiency: Hugging Face smolagents!

๐Ÿ”— URL: agents-course

We just published the LlamaIndex unit for the agents course, and it is set to offer a great contrast between the smolagents unit by looking at

- What makes llama-index stand-out
- How the LlamaHub is used for integrations
- Creating QueryEngine components
- Using agents and tools
- Agentic and multi-agent workflows

The team has been working flat-out on this for a few weeks. Supported by Logan Markewich and Laurie Voss over at LlamaIndex.

Who won? You decide!
posted an update 2 months ago
view post
Post
3042
๐Ÿซธ New release to push vector search to the Hub with vicinity and work with any serialisable objects.

๐Ÿง‘โ€๐Ÿซ KNN, HNSW, USEARCH, ANNOY, PYNNDESCENT, FAISS, and VOYAGER.

๐Ÿ”— Example Repo: minishlab/my-vicinity-repo
reacted to jsulz's post with โค๏ธโž•๐Ÿš€ 3 months ago
view post
Post
3121
Toward the end of last year, the Xet team provided an inside look into the foundations of how we plan to enable rapid experimentation and iteration for the AI builders on the Hub: https://huggingface.co/blog/from-files-to-chunks

But it turns out chunks aren't all you need!

Our goal is to bring:
๐Ÿš€ Faster uploads
โฌ Speedy downloads
๐Ÿ’ช All without sacrificing your workflow

To do that, we need the infrastructure and system and design to back it up. As we prepare to roll out the first Xet-backed repositories on the Hub, we wrote up a post explaining the nitty gritty details of the decisions that bring this to life https://huggingface.co/blog/from-chunks-to-blocks

Complete with an interactive visualization that shows the power of deduplication in action - taking a 191GB repo to ~97GB and shaving a few hours off upload speeds.

The darker each block in the heatmap, the more we dedupe, the less we have to transfer. Clicking on a file's blocks shows all other files that share blocks.

Check it out and explore for yourself! xet-team/quantization-dedup
posted an update 3 months ago
view post
Post
3311
๐Ÿš€ Find banger tools for your smolagents!

I created the Tools gallery, which makes tools specifically developed by/for smolagents searchable and visible. This will help with:
- inspiration
- best practices
- finding cool tools

Space: davidberenstein1957/smolagents-and-tools
  • 1 reply
ยท
reacted to their post with ๐Ÿ‘€ 3 months ago
reacted to ZennyKenny's post with โค๏ธ๐Ÿ˜Ž๐Ÿค—๐Ÿ”ฅ 3 months ago
view post
Post
3463
I've completed the first unit of the just-launched Hugging Face Agents Course. I would highly recommend it, even for experienced builders, because it is a great walkthrough of the smolagents library and toolkit.
posted an update 3 months ago