Shawn Fumo

InvidFlower

AI & ML interests

None yet

Recent Activity

commentedon an article about 2 months ago

Security incident disclosure — July 2026

liked a model over 1 year ago

microsoft/bitnet-b1.58-2B-4T

upvoted a paper over 1 year ago

KBLaM: Knowledge Base augmented Language Model

View all activity

Organizations

None yet

commented on Security incident disclosure — July 2026 about 2 months ago

For those that haven't seen it yet, it sounds like this entire thing was OpenAI running a benchmark. Ends up the models found a zero-day in the package proxy to get internet access and hacked into Hugging Face to try to get the answers to the ExploitGym benchmark. Crazy stuff: https://openai.com/index/hugging-face-model-evaluation-security-incident/

liked a model over 1 year ago

microsoft/bitnet-b1.58-2B-4T

Text Generation • 0.8B • Updated Dec 17, 2025 • 23.3k • 1.49k

upvoted a paper over 1 year ago

KBLaM: Knowledge Base augmented Language Model

Paper • 2410.10450 • Published Oct 14, 2024 • 2

liked a model over 1 year ago

Steelskull/L3.3-Electra-R1-70b

Text Generation • 71B • Updated Jun 18, 2025 • 35 • • 61

upvoted 2 papers over 1 year ago

DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

Paper • 2503.15265 • Published Mar 19, 2025 • 46

TULIP: Towards Unified Language-Image Pretraining

Paper • 2503.15485 • Published Mar 19, 2025 • 49

liked 3 Spaces over 1 year ago

FineWeb: decanting the web for the finest text data at scale

Explore and download the FineWeb web‑scale text dataset

The Ultra-Scale Playbook

The ultimate guide to training LLM on large GPU Clusters

Predict Memory

Estimate model memory usage and see detailed plots

upvoted a paper over 1 year ago

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Paper • 2501.04519 • Published Jan 8, 2025 • 290

liked a model about 2 years ago

zai-org/CogVideoX-5b

Text-to-Video • 6B • Updated Nov 23, 2024 • 18.2k • • 686

liked a Space about 2 years ago

CogVideoX-5B

Text-to-Video

liked a model about 2 years ago

dooart/flux-lora-vintage-tarot

Text-to-Image • Updated Aug 25, 2024 • 20 • • 17

commented 3 papers over 2 years ago

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22, 2024 • 262 •

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22, 2024 • 262 •

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 630 •

liked a model over 2 years ago

kousw/bitnet_b1_58-3B_quantized

Text Generation • 0.3B • Updated Mar 31, 2024 • 15 • 12

commented 2 papers over 2 years ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 630 •

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27, 2024 • 630 •

liked a model over 2 years ago

HuggingFaceH4/zephyr-7b-beta

Text Generation • 7B • Updated Oct 16, 2024 • 65.6k • • 1.85k