Only 6 of ERNIE 5.5 Flash Base's 43 layers see every token individually
This is a AI post classified by AGK Intelligence as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
Only 6 of ERNIE 5.5 Flash Base's 43 layers see every token individually >the other 37 squash every 128 tokens into 1 cached entry, plus a short window of recent tokens >those cheap layers get wide 512-dim heads, the 6 full-context layers get 256-dim >the 6 full-context layers use sparse attention, only over the top-k scored positions >still beats DeepSeek V4 Flash Base on 4 of 6 long-context benchmarks Baidu built the KV cache on a diet
Posted by Binkg (14.3k followers) 1 h ago · 5 likes · 671 views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- Baidu just dropped ERNIE-5.5-Flash-Base, and the weights are available. — @kimmonismus
- Anthropic内部还有3个能力强于Opus 5.5的模型。根据Metr的披露，最强模型是Model 4，178.6分，而Opus 5.5 只有174.56分 — @mylifcc
- Voici un exemple de raisonnement stratégique que GPT-6 Astra met en œuvre en jouant… — @Fabien_Mikol
- Qwen 4.0要来了！ — @NFT_Chen
- Baidu killed the MTP module everyone copied from DeepSeek — @dummerspast39
- Baidu killed the MTP module everyone copied from DeepSeek — @dummerspast39
- ALIBABA 🔥: "The becoming begins" teaser has been posted on the Qwen X account. We… — @testingcatalog
- Qwen 4??? — @niklaslenz_ai
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.7k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 13:30 UTC. Full method.