21 38 62

Tony Wu

tonywu71

AI & ML interests

LLM, Multimodal, Agents, Information Retrieval, RAG, Speech

Recent Activity

upvoted a paper 14 days ago

Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models

upvoted an article 14 days ago

DeepSeek-V4: a million-token context that agents can actually use

liked a Space 2 months ago

HuggingFaceFW/finephrase

View all activity

Organizations

liked a Space 2 months ago

The Synthetic Data Playbook: Generating Trillions of the Finest Tokens

📝

232

Explore synthetic data experiments on a virtual bookshelf

liked a Space 5 months ago

Evaluation Guidebook

📝

316

Explore LLM benchmark trends over time

liked a Space 6 months ago

The Smol Training Playbook

📚

3.16k

The secrets to building world-class LLMs

liked 2 Spaces 8 months ago

Holo1.5 Localization

🌍

Holo1.5 Localization: High-Resolution UI Grounding

Holo1.5 Navigation

🐢

Holo1.5 Navigation: GUI Action Model

liked 3 models 8 months ago

liked a model 11 months ago

Hcompany/Holo1-3B

Image-Text-to-Text • 4B • Updated Jun 10, 2025 • 571 • 83

liked a model 12 months ago

nomic-ai/colnomic-embed-multimodal-7b

Visual Document Retrieval • Updated Apr 15, 2025 • 4.99k • 105

liked a Space about 1 year ago

Open ASR Leaderboard

🏆

1.33k

Explore and compare speech recognition model benchmarks

liked a model about 1 year ago

Qwen/Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Jan 12, 2025 • 14.4M • • 1.27k

liked 3 Spaces about 1 year ago

Arena Leaderboard

🏆

4.88k

View the LMArena model leaderboard

MTEB Leaderboard

🥇

7.35k

Embedding Leaderboard

The Ultra-Scale Playbook

🌌

3.83k

The ultimate guide to training LLM on large GPU Clusters

liked a model over 1 year ago

HuggingFaceTB/SmolLM-1.7B

Text Generation • 2B • Updated Oct 16, 2024 • 45.3k • 181

liked a Space over 1 year ago

GAIA Leaderboard

🦾

604

Submit and score your model on the GAIA benchmark

liked 3 models over 1 year ago

mistralai/Mistral-Small-24B-Instruct-2501

Updated Jul 28, 2025 • 93.5k • 950

Qwen/Qwen2.5-7B-Instruct-1M

Text Generation • 8B • Updated Jan 29, 2025 • 41k • • 369

Qwen/Qwen2-VL-2B

Image-Text-to-Text • 2B • Updated Dec 6, 2024 • 2.78k • 64