David Berenstein PRO

davidberenstein1957's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article 21 days ago

view article

Article

Phare LLM benchmark V2: Reasoning models don't guarantee better security

• 

21 days ago

•

10

upvoted an article about 1 month ago

view article

Article

Transformers v5: Simple model definitions powering the AI ecosystem

• 
• 
• +2

Dec 1, 2025

•

265

upvoted an article about 2 months ago

view article

Article

AI Model Optimization More Flexible Than Ever

• 

Nov 17, 2025

•

13

upvoted 2 collections about 2 months ago

SmolLM-Smashed: Tiny Giants, Optimized for Speed

Collection

SmolLM-Smashed is a collection of optimized language models. Each model is quantized and compiled for maximum efficiency while preserving performance. • 5 items • Updated Oct 4, 2025 • 1

NanoBEIR 🍺

Collection

A collection of smaller versions of BEIR datasets with 50 queries and up to 10K documents each. • 13 items • Updated Sep 11, 2024 • 23

upvoted an article about 2 months ago

view article

Article

Effective Prompting for Generative Vision Models

• 

Nov 10, 2025

•

9

upvoted 2 articles 2 months ago

view article

Article

Building the Open Agent Ecosystem Together: Introducing OpenEnv

• 
• 
• +8

Oct 23, 2025

•

139

view article

Article

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

• 
• 
• +7

Jun 3, 2025

•

305

upvoted a collection 2 months ago

gpt-oss-safeguard

Collection

gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss • 2 items • Updated Oct 29, 2025 • 58

upvoted an article 3 months ago

view article

Article

Sentence Transformers is joining Hugging Face!

• 

Oct 22, 2025

•

86

upvoted a paper 4 months ago

Deep Think with Confidence

Paper • 2508.15260 • Published Aug 21, 2025 • 90

upvoted 2 collections 5 months ago

FLUX.1

Collection

A collection of our FLUX.1 models and LoRAs. • 13 items • Updated 4 days ago • 259

💧 LFM2

Collection

LFM2 is a new generation of hybrid models, designed for on-device deployment. • 26 items • Updated about 15 hours ago • 131

upvoted an article 5 months ago

view article

Article

Learn the Hugging Face Kernel Hub in 5 Minutes

• 
• 
• +5

Jun 12, 2025

•

151

upvoted a collection 6 months ago

LLaVA-1.5

Collection

A collection of LLaVA-1.5 checkpoints • 4 items • Updated Jan 31, 2024 • 24

upvoted 2 articles 6 months ago

view article

Article

Vibe coding for data science: how to label a dataset with Kimi K2

• 

Jul 22, 2025

•

21

view article

Article

RealPerformance, A Dataset of Language Model Business Compliance Issues

• 

Jul 21, 2025

•

4

upvoted a collection 6 months ago

Nunchaku

Collection

10 items • Updated Jun 29, 2025 • 35

upvoted 2 articles 6 months ago

view article

Article

LLM Hallucinations: bug or feature? The US Supreme Court 2025 cases experiment

• 

Jul 8, 2025

•

19

view article

Article

LLMs recognise bias but also reproduce harmful stereotypes: an analysis of bias in leading LLMs

• 

Jul 2, 2025

•

16