把对话语言模型压到 2-bit 量化,小到能在 8 位 Z80 处理器上跑,用 Python 训练后导出成 CP/M 的 .COM 程序,让老电脑也能聊天。
What's changed - Added Claude Fable 5.2 ( claude-fable-5-2 ), now the default Fable model — 1M context, $8/$40 per Mtok with $0.20/Mtok cache reads - Added --se
…le to be persisted; low-risk file commands (mkdir/cp/mv/touch/rmdir) are relaxed to command-name prefix rules. - Stability & Bash safety : the whole-UI freeze caused by p
What's Changed chore(swe): remove unused SWE SFT dataset loader by @Le8r0nJames in https://github.com/areal-project/AReaL/pull/1467 fix(docker): rename zeroclaw
Compute Fabric Transport (CFT) - Adds CFT host and device APIs for registering window memory with CUDA logical endpoints and issuing device-side Put, Get, Red a
New features Improved performance, accuracy, memory consumption, and stability, with particular focus on new models featuring linear attention architectures lik
…ility issues in DeepSeek-3.2 scenarios. - Improve CP/MTP compatibility behavior in edge cases. - Fix etcd auth and service registration related reliability issues. - Addr