Unverified50% confidenceOpinionExact time
The paper attributes the gap of Manacá-1B-Instruct-2 in general capabilities to pretraining scale (a comparison of compute budgets anchored on Chinchilla) rather than to the alignment method itself.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedChinchilla论文修正了预训练中计算与数据的最优比例关系71% similarVerifiedDeepMind's Chinchilla research (2022) pointed out that optimal training should keep data volume and parameter count growing at roughly a 1:1 ratio70% similarUnverified根据Chinchilla定律及其后续研究，模型性能与训练计算量之间存在幂律关系69% similarUnverified诊断训练瓶颈的核心效率差异来自于是否提前建立了性能基线（baseline），如已知模型健康状态下的MFU则可快速发现偏离69% similarVerifiedIn 2022, DeepMind's Chinchilla paper pointed out that under the same compute budget, model size and training data volume should be scaled up proportionally.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1032796API
curl https://kongchang.com/api/v1/knowledge/claims/1032796MCP
get_claim(id=1032796)