Unverified50% confidenceFactExact time
ResQAdam maintains only a single BF16-precision momentum, applies the Adam update only to the r×r coordinates of the dominant singular subspace, and adds a normalized sign update computed from the residual.
1
Sources
50%
Confidence
Long-term
Relevance
11/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUnsloth changed the default GGUF precision for Qwen-Image-2.1 from F16/BF16 to Q4_K_M.60% similarUnverified开发者采取混合精度策略,将对质量敏感的层保留在BF16,仅对能从FP8获益的部分做转换58% similarUnverifiedThe V4.1 architecture is robust to quantization, with accuracy loss on the MMLU benchmark of less than 0.2% when switching from FP16 to FP8.58% similarUnverifiedNVFP4 quantization is not 4-bit for the whole model: the vision encoder, connector, Mamba convolutions, and embedding stay in BF16, and the MoE router stays in FP32.58% similarUnverifiedThe M5 Ultra's FP8 and FP4 floating-point compute performance is identical to its BF16 performance, and the gap with the Spark narrows noticeably when dropping to FP4 precision.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1149982API
curl https://kongchang.com/api/v1/knowledge/claims/1149982MCP
get_claim(id=1149982)