❤️ DeepSeek V4.1 Flash 1017!!!

brulee

brulee-1

·

https://brulee.tech

AI & ML interests

efficiency

Recent Activity

liked a model about 4 hours ago

MiniMaxAI/MiniMax-M3.1-Flash

liked a model 1 day ago

RecursiveSI/flint

liked a model 3 days ago

XHToken/Spark-X2.6-4B

View all activity

Organizations

upvoted a changelog 3 days ago

Hugging Face Changelog

Filter Models & Datasets Pages by Author

7 days ago

• 84

upvoted a collection 7 days ago

Beam 1.0

Reflection’s first open-weight model, built for coding, reasoning, and agentic tasks • 4 items • Updated 7 days ago • 44

upvoted a collection 10 days ago

MiniCPM-V 4.7

A new chapter in on-device multimodal Al. • 15 items • Updated 9 days ago • 74

upvoted a paper 14 days ago

TokenRouter: Efficient Serving System for Token-Level LLM Routing

Paper • 2610.12242 • Published 16 days ago • 146

upvoted a collection 14 days ago

Mellum2.1

Mellum2.1 model weights • 2 items • Updated 15 days ago • 30

upvoted a paper 14 days ago

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Paper • 2610.11959 • Published 16 days ago • 93

upvoted a changelog 14 days ago

Hugging Face Changelog

Decision Models on the Hub

14 days ago

• 228

upvoted a paper 14 days ago

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Paper • 2609.38169 • Published 25 days ago • 74

upvoted a changelog 16 days ago

Hugging Face Changelog

P(doom) on user profiles

18 days ago

• 363

upvoted a paper 19 days ago

Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It

Paper • 2609.36585 • Published 25 days ago • 42

upvoted a collection 20 days ago

Kolibri-1

2 items • Updated 20 days ago • 14

upvoted a collection 21 days ago

Kev

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own • 6 items • Updated 22 days ago • 35

upvoted a collection 23 days ago

LTX-2.5 Creative Lab

15 items • Updated 22 days ago • 30

upvoted a collection 24 days ago

Intern-Decision

5 items • Updated 7 days ago • 25

upvoted a paper 25 days ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 29 days ago • 121

upvoted 4 collections 25 days ago

Holo4

State-of-the-art Visual Language Model (VLM) for computer/mobile use, tool calls, and code. • 11 items • Updated 25 days ago • 44

Qwen3.8-3.6-27B Blend

Junie Local's unofficial JetBrains 50/50 blend of Qwen3.6-27B and Qwen3.8-27B: BF16, GGUF, and MLX weights. • 5 items • Updated 25 days ago • 10

LLM-jp-4.1 Post-Training Dataset

4 items • Updated 25 days ago • 2

LLM-jp-4.1 Models

6 items • Updated 25 days ago • 10

upvoted a paper 25 days ago

OmniEcho: Spatial Audio Understanding for Embodied Agents

Paper • 2609.23407 • Published Sep 20 • 35