David Berenstein PRO

davidberenstein1957's activity

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

upvoted an article about 1 hour ago

view article

Article

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

• 

Jan 27

•

68

upvoted a changelog 14 days ago

view changelog

Hugging Face Changelog

Introducing Buckets: S3-like storage on the Hub

22 days ago

• 183

upvoted a collection 15 days ago

LTX-2.3

Collection

LTX-2.3 base models, quantized models and accompanying LoRAs and IC-LoRAs • 6 items • Updated 16 days ago • 32

upvoted an article 26 days ago

view article

Article

Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines

• 
• 
• +2

27 days ago

•

47

upvoted an article 28 days ago

view article

Article

LLM Architectures Explained: What Powers Today’s Top Models

• 

28 days ago

•

8

upvoted 2 articles about 1 month ago

view article

Article

Training Design for Text-to-Image Models: Lessons from Ablations

• 

Feb 3

•

69

view article

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

• 
• 
• +4

Feb 20

•

490

upvoted a collection about 1 month ago

GLiCLass-V3

Collection

Models for zero-shot text classification that are up to 50 times faster than Cross-Encoders and show the same or higher accuracy. • 8 items • Updated Jan 29 • 20

upvoted 3 articles 2 months ago

view article

Article

Introducing Daggr: Chain apps programmatically, inspect visually

• 
• 
• +3

Jan 29

•

106

view article

Article

We Got Claude to Build CUDA Kernels and teach open models!

• 
• 
• +2

Jan 28

•

152

view article

Article

Slashing torch.compile Warmup & LoRA Swapping Times with Pruna

• 

Jan 28

•

5

upvoted 2 collections 2 months ago

Z-Image

Collection

7 items • Updated Jan 28 • 147

LTX-2

Collection

LTX-2 base models and accompanying LoRAs and IC-LoRAs • 13 items • Updated Jan 29 • 56

upvoted 2 articles 3 months ago

view article

Article

SmolLM-Smashed: Tiny Giants, Optimized for Speed

• 

Jan 13

•

15

view article

Article

How to Choose the Best Open Source LLM for Your Project in 2025

• 

Sep 9, 2025

•

75

upvoted 3 articles 4 months ago

view article

Article

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

• 

Dec 16, 2025

•

10

view article

Article

Transformers v5: Simple model definitions powering the AI ecosystem

• 
• 
• +2

Dec 1, 2025

•

307

view article

Article

AI Model Optimization More Flexible Than Ever

• 

Nov 17, 2025

•

13

upvoted 2 collections 5 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 20 days ago • 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 • 26