Florent Daudens's picture

Florent Daudens

fdaudens

·

AI & ML interests

AI & Journalism

Recent Activity

liked a model about 8 hours ago

all-hands/openhands-lm-32b-v0.1

posted an update about 13 hours 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

liked a Space about 13 hours ago

yourbench/demo

View all activity

Organizations

fdaudens's activity

upvoted a paper 3 days ago

CountGD: Multi-Modal Open-World Counting

Paper • 2407.04619 • Published Jul 5, 2024 • 2

upvoted an article 6 days ago

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

8 days ago

• 92

upvoted a collection 13 days ago

March 21 Releases

39 items • Updated 12 days ago • 10

upvoted a collection 14 days ago

Orpheus TTS

TTS Towards Human-Sounding Speech • 2 items • Updated 15 days ago • 52

upvoted 3 collections 20 days ago

👩‍💻 OlympicCoder

Reasoning datasets and models for competitive coding • 4 items • Updated 23 days ago • 16

OLMo 2

Artifacts for the second set of OLMo models. • 27 items • Updated 14 days ago • 107

Meta's Llama 3.2 language models & evals

14 items • Updated Dec 13, 2024 • 137

upvoted 2 collections 21 days ago

Gemma 3

A collection of lightweight, state-of-the-art open models built from the same research and technology that powers the Gemini 2.0 models • 31 items • Updated 22 days ago • 22

Gemma 3 Release

17 items • Updated 7 days ago • 304

upvoted an article 21 days ago

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

22 days ago

• 364

upvoted an article 23 days ago

Article

LeRobot goes to driving school: World’s largest open-source self-driving dataset

23 days ago

• 70

upvoted an article 29 days ago

Article

Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥

Feb 18

• 95

upvoted 2 collections about 1 month ago

olmOCR

olmOCR is a document recognition pipeline for efficiently converting documents into plain text. olmocr.allenai.org • 4 items • Updated 15 days ago • 102

Phi-4

Phi-4 family of small language and multi-modal models. • 7 items • Updated about 1 month ago • 111

upvoted 2 articles about 1 month ago

Article

FastRTC: The Real-Time Communication Library for Python

Feb 25

• 152

Article

SigLIP 2: A better multilingual vision language encoder

Feb 21

• 148