AI Safety Research

AISafety's activity

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

liked a model about 7 hours ago

PowerInfer/SmallThinker-3B-Preview

Text Generation • Updated about 15 hours ago • 367 • • 156

liked a model about 8 hours ago

bartowski/QVQ-72B-Preview-GGUF

Image-Text-to-Text • Updated 9 days ago • 66.3k • 45

liked a Space about 8 hours ago

Running

382

🌍

QVQ 72B Preview

liked a dataset 26 days ago

gretelai/gretel-math-gsm8k-v1

Viewer • Updated Oct 16, 2024 • 24.9k • 466 • 40

New activity in Qwen/QwQ-32B-Preview 28 days ago

QuietSTAR?

1

#9 opened about 1 month ago by

albatrossbirdie

liked 2 models about 1 month ago

1aurent/distilbert-base-multilingual-cased-finetuned-email-spam

Text Classification • Updated Aug 27, 2023 • 63 • 2

mrm8488/bert-tiny-finetuned-enron-spam-detection

Text Classification • Updated Mar 17, 2023 • 13.6k • 8

liked 2 datasets about 1 month ago

simecek/czech_news

Viewer • Updated Oct 24, 2024 • 1k • 32 • 1

SetFit/enron_spam

Viewer • Updated Jan 16, 2022 • 33.7k • 850 • 19

liked 2 models about 1 month ago

avsolatorio/NoInstruct-small-Embedding-v0

Sentence Similarity • Updated May 4, 2024 • 61k • 14

avsolatorio/GIST-small-Embedding-v0

Sentence Similarity • Updated Feb 28, 2024 • 259k • 24

liked a dataset about 1 month ago

sproos/arxiv_embeddings_480k

Viewer • Updated Oct 16, 2023 • 481k • 55 • 2

New activity in dagim/urban-dictionary-embeddings about 1 month ago

size flag is off

#1 opened about 1 month ago by

AISafety

liked a model about 1 month ago

intfloat/multilingual-e5-large-instruct

Feature Extraction • Updated Sep 26, 2024 • 246k • • 257

liked a dataset about 1 month ago

Cohere/wikipedia-22-12-en-embeddings

Viewer • Updated Mar 22, 2023 • 35.2M • 2.4k • 62

liked a model about 1 month ago

Zhengyi/LLaMA-Mesh

Text-to-3D • Updated 27 days ago • 3.74k • 91

liked a Space about 1 month ago

Running

1.24k

🐢

Qwen2.5 Coder Artifacts

reacted to hbseong's post with 🔥 about 1 month ago

view post

Post

922

🚨🔥 New Release Alert! 🔥🚨

Introducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! 💻💥
👉 Check it out: hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! 💡)

More details in our paper: https://arxiv.org/abs/2410.01524 📜

#HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning

• 
• 1 reply

·

👀

5

5

🔥

4

4

+

Reply

liked a Space about 1 month ago

Running

310

💻

Qwen2.5 Turbo 1M Demo

upvoted an article 2 months ago

view article

Article

Decoding Strategies in Large Language Models

By •

Oct 29, 2024

• 38