4 18 9

Jesse

jessepisel

jessepisel

AI & ML interests

computer vision, generative ai, agentic

Recent Activity

reacted to clem's post with 🔥 3 days ago

Llama models (arguably the most successful open AI models of all times) just represented 3% of total model downloads on Hugging Face in March. People and media like stories of winner takes all & one model/company to rule them all but the reality is much more nuanced than this! Kudos to all the small AI builders out there!

liked a Space 5 days ago

yourbench/demo

reacted to fdaudens's post with 🔥 5 days ago

Did we just drop personalized AI evaluation?! This tool auto-generates custom benchmarks on your docs to test which models are the best. Most benchmarks test general capabilities, but what matters is how models handle your data and tasks. YourBench helps answer critical questions like: - Do you really need a hundreds-of-billions-parameter model sledgehammer to crack a nut? - Could a smaller, fine-tuned model work better? - How well do different models understand your domain? Some cool features: 📚 Generates custom benchmarks from your own documents (PDFs, Word, HTML) 🎯 Tests models on real tasks, not just general capabilities 🔄 Supports multiple models for different pipeline stages 🧠 Generate both single-hop and multi-hop questions 🔍 Evaluate top models and deploy leaderboards instantly 💰 Full cost analysis to optimize for your budget 🛠️ Fully configurable via a single YAML file 26 SOTA models tested for question generation. Interesting finding: Qwen2.5 32B leads in question diversity, while smaller Qwen models and Gemini 2.0 Flash offer great value for cost. You can also run it locally on any models you want. I'm impressed. Try it out: https://huggingface.co/spaces/yourbench/demo

View all activity

Organizations

jessepisel's activity

upvoted a paper 11 days ago

Open Deep Search: Democratizing Search with Open-source Reasoning Agents

Paper • 2503.20201 • Published 13 days ago • 42

upvoted a paper 26 days ago

Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning

Paper • 2503.04973 • Published Mar 6 • 21

upvoted a paper about 1 month ago

LLM as a Broken Telephone: Iterative Generation Distorts Information

Paper • 2502.20258 • Published Feb 27 • 26

upvoted a paper 2 months ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4 • 220

upvoted a collection 2 months ago

Tulu 3 Models

Collection

All models released with Tulu 3 -- state of the art open post-training recipes. • 11 items • Updated 25 days ago • 96

upvoted 2 articles 2 months ago

Article

Welcome to Inference Providers on the Hub 🔥

Jan 28

• 460

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

• 835

upvoted 3 papers 4 months ago

upvoted a paper 5 months ago

Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models

Paper • 2411.04996 • Published Nov 7, 2024 • 51

upvoted 2 papers 6 months ago

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Paper • 2410.02707 • Published Oct 3, 2024 • 48

LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness

Paper • 2409.18125 • Published Sep 26, 2024 • 34

upvoted 2 papers 7 months ago

SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction

Paper • 2409.11211 • Published Sep 17, 2024 • 9

Implicit Neural Representations with Fourier Kolmogorov-Arnold Networks

Paper • 2409.09323 • Published Sep 14, 2024 • 5