We’re open-sourcing our text-to-image model and the process behind it
•
65
We’re open-sourcing our text-to-image model and the process behind it
•
65
Text-to-image Architectural Experiments
•
31
Introducing Cogito v2.1
•
16
Projected Abliteration
•
26
AI Model Optimization More Flexible Than Ever
•
12
ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases
•
49
The Heterogeneous Feature of RoPE-based Attention in Long-Context LLMs
•
11
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
175
Norm-Preserving Biprojected Abliteration
•
14
Uncensor any LLM with abliteration
•
721
Why Did MiniMax M2 End Up as a Full Attention Model?
•
65
The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix
•
42
The Pharmome Map: a comprehensive public dataset for drug-target interaction modeling
•
8
Granite 4.0 Nano: Just how small can you go?
•
119
Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models
•
7
Visualizing How VLMs Work
•
45
🧠 SQaLe: Enabling new Text-to-SQL models with our massive dataset
•
6
Join the AMD Open Robotics Hackathon
•
6
To Think or Not to Think: A Router for Hybrid LLMs
•
6
PEFT: Parameter-Efficient Fine-Tuning Methods for LLMs
•
49