Unverified50% confidenceFactExact time
Wolf Defender v2 employs mixed training combining short samples (256 tokens) with a full long window (2048 tokens).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/31/2026
First Seen
Valid until: 11/29/2026
Sources
Related Entities
Related Claims
UnverifiedThe Wolf Defender main model's real-world benign specificity improved from 66.85% in v1 to 96.63% in v2.62% similarUnverifiedWolf Defender v2's attack detection capability is largely maintained at its original level, with a Qualifire F1 of 95.14% and a Jayavibhav F1 of 97.84%.62% similarUnverifiedIn token generation tests for the Gemma 4 12B model, Spark reached 26.4 tokens/s, Halo 24.6 tokens/s, and M4 Pro was the fastest at 33.8 tokens/s.58% similarUnverifiedAccording to the Chinchilla scaling law, the optimal training data volume for a 30B model is approximately 600B–1T tokens.55% similarUnverifiedMiniMax M3 每个 token 推理时约激活 23B 参数54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/827594API
curl https://kongchang.com/api/v1/knowledge/claims/827594MCP
get_claim(id=827594)