Transformer co-creator Vaswani unveils high-performance Rnj-1 coding model - the-decoder.com
Transformer co-creator Vaswani unveils high-performance Rnj-1 coding model the-decoder.com
Could not retrieve the full article text.
Read on GNews AI transformer →Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
modeltransformerb8648
ggml-zendnn : add MUL_MAT_ID op support for MoE models ( #21315 ) ggml-zendnn : add MUL_MAT_ID op support for MoE models Add MUL_MAT_ID op acceleration for Mixture-of-Experts models MUL_MAT_ID op fallback to CPU backend if total experts > 32 Point ZenDNN lib to latest bits ZenDNN-2026-WW13 ggml-zendnn : add braces to sgemm failure condition for consistency Co-authored-by: Aaron Teo [email protected] Co-authored-by: Aaron Teo [email protected] macOS/iOS: macOS Apple Silicon (arm64) macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (ROCm 7.2) Ubuntu x64 (OpenVINO) Windows: Windows x64 (CPU) Windows arm64 (CPU) Windows x64 (CUDA 12) - CUDA 12.4 DLLs Windows x64 (CUDA 13) - CUDA 13.1 DLLs Windo
![[P] I trained a Mamba-3 log anomaly detector that hit 0.9975 F1 on HDFS — and I’m curious how far this can go](https://d2xsxph8kpxj0f.cloudfront.net/310419663032563854/konzwo8nGf8Z4uZsMefwMr/default-img-neural-network-P6fqXULWLNUwjuxqUZnB3T.webp)
[P] I trained a Mamba-3 log anomaly detector that hit 0.9975 F1 on HDFS — and I’m curious how far this can go
Experiment #324 ended well. ;) This time I built a small project around log anomaly detection. In about two days, I went from roughly 60% effectiveness in the first runs to a final F1 score of 0.9975 on the HDFS benchmark. Under my current preprocessing and evaluation setup, LogAI reaches F1=0.9975, which is slightly above the 0.996 HDFS result reported for LogRobust in a recent comparative study. What that means in practice: on 3,368 anomalous sessions in the test set, it missed about 9 (recall = 0.9973) on roughly 112k normal sessions, it raised only about 3 false alarms (precision = 0.9976) What I find especially interesting is that this is probably the first log anomaly detection model built on top of Mamba-3 / SSM, which was only published a few weeks ago. The model is small: 4.9M par
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!