Nicholas Broad

nbroad's activity

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

upvoted a paper 2 days ago

Fully Autonomous AI Agents Should Not be Developed

Paper • 2502.02649 • Published Feb 4 • 33

liked a Space 5 days ago

Running

268

268

Repo duplicator

😻

Copy a Hugging Face repository

liked a model 7 days ago

Qwen/Qwen2.5-Omni-7B

Any-to-Any • Updated 2 days ago • 61.8k • 1.06k

New activity in LGAI-EXAONE/EXAONE-Deep-2.4B 9 days ago

Chat template difference with 32b

3

#2 opened 12 days ago by

nbroad

upvoted a paper 16 days ago

Charting and Navigating Hugging Face's Model Atlas

Paper • 2503.10633 • Published 20 days ago • 71

liked a Space 23 days ago

Running on Zero

525

525

Di♪♪Rhythm

🎶

Blazingly Fast and Embarrassingly Simple Song Generation

New activity in Qwen/QwQ-32B 27 days ago

remove part about long context modifications

#32 opened 27 days ago by

nbroad

New activity in ahmedmbutt/PTS-Dataset 27 days ago

How did you make this dataset?

#2 opened 27 days ago by

nbroad

liked a model 28 days ago

Qwen/QwQ-32B

Text Generation • Updated 22 days ago • 787k • • 2.61k

upvoted a paper about 1 month ago

NeoBERT: A Next-Generation BERT

Paper • 2502.19587 • Published Feb 26 • 38

liked a model about 1 month ago

microsoft/wham

Updated Feb 21 • 769 • 250

liked a Space about 1 month ago

Running

2.4k

2.4k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

upvoted an article about 1 month ago

view article

Article

1 Billion Classifications

Feb 13

• 43

commented on 🪆 Introduction to Matryoshka Embedding Models about 1 month ago

view reply

So you are saying to normalize once with all dimensions, then normalize again after truncation?

commented on 🪆 Introduction to Matryoshka Embedding Models about 1 month ago

view reply

@tomaarsen ,

Great article! Regarding normalizing: should it happen before or after truncation?

liked 2 models about 1 month ago

zed-industries/zeta

Updated Feb 27 • 2.84k • 253

microsoft/OmniParser-v2.0

Updated 5 days ago • 4.95k • 1.2k

upvoted 2 papers about 1 month ago

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Paper • 2502.11089 • Published Feb 16 • 150

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

Paper • 2502.12115 • Published Feb 17 • 43