Unverified50% confidenceOpinionExact time
For medium-scale models directly generating high-quality legal headnotes, the marginal benefit of pure supervised fine-tuning is limited.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe core insight of AWQ is that only approximately 1% of salient weights have a major impact on model output, and protecting them enables model quality to be maintained at extremely low bit widths67% similarUnverified权重绑定在中小规模模型上(如GPT-2 124M)通常能提升性能并减少约30%的嵌入相关参数，但在超大规模模型中收益递减64% similarUnverifiedIn MoE models, dense layer parameters typically account for less than 20% of total parameters, but every token must pass through them, so they require higher-precision protection.63% similarUnverifiedA sparse model with a huge total parameter count may have far lower inference costs than a smaller dense model63% similarUnverified自回归缩放定律的边际收益正在递减，单纯增加模型规模和数据量带来的提升已微乎其微63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/910239API
curl https://kongchang.com/api/v1/knowledge/claims/910239MCP
get_claim(id=910239)