跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1295新增论文
+1026其中 AI 相关
+111已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 16:10各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 17:10 — 2026-11-17 17:10(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-17 04:58最近发现新增版本:2026-11-17 16:10库内论文最新更新时间:2026-11-17 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

25,122 已收录论文20,967 AI 相关7,309 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
版本更新 · v3arXiv:2610.07853

Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes

Avichal Sahai, Nishant Raj, Animesh Srivastava

原文摘要

Ternary language models such as BitNet b1.58, Falcon-E and BitCPM are fine-tuned through higher-precision latents and deployed as ternary codes by an export that, in the labs' documented pipelines, first casts latents to bf16. We audit releases from three labs. In released checkpoints, fp32 quantization of the shipped latents disagrees with deployed codes on 0.83-1.77% of codes (Falcon-E, BitCPM) and 1.530% (2B-4T); most Falcon-E and BitCPM disagreements are bf16 products exactly on the threshold, which ties-to-even maps to zero, and the unmodified onebitllms exporter reproduces all four Falcon-E releases byte for byte. At fine-tuned endpoints with ULP-matched rates, the documented export lowers greedy GSM8K strict accuracy from 58.79% to 0.78% (Falcon-E-1B-Base) and 36.13% to 0.39% (BitCPM-CANN-0.5B), and a bf16 save and reload lowers 2B-4T's by 27.54 points while its last-number accuracy rises at that endpoint. The strict decrease recurs at each of three new seeds in all three models and has the same direction on 607 reserve test rows, but it is recipe-dependent: at Falcon-E's online-loss-selected rate the export was non-inferior, and after a longer recipe no difference was detected. Two remedies, writing the trained codes directly or adjusting bf16 inputs so unchanged tools emit them, met an inherited 4-point strict-accuracy non-inferiority criterion in all three models, also for the pooled mean over three fixed new trajectories per model and, separately, on the reserve rows. In a frozen study of bf16 latents in fine-tuning (one task, one trajectory per arm), native bf16 writes left 2B-4T's endpoint codes unchanged and changed one Falcon-E code; emulated stochastic-rounding and compensated writers changed codes and were non-inferior to fp32 training at that margin. In two model families, randomized threshold-distance interventions support distance-dependent selection of changed codes.

cs.LG · cs.CL