jevIMAGE
训练 TERN-35B-A3B 探索 Jev 决策模型的价格前沿
作者为探索 Jev 决策模型的价格前沿而训练 TERN-35B-A3B，在 H100 PCIE 上将成本降至 $0.0116/Mtok，优化后达到 $0.00773/Mtok。
Matt
@Matthewagi6 天前收录原推发布于 2026.10.23
Matt @Matthewagi原推发布于 2026.10.23
The goal of @typesafeai Jev model is to unlock Jevon's paradox. I wanted to play around with decision models so I trained TERN-35B-A3B. The goal is price frontier. On an H100 PCIE I got it to $0.0116/Mtok. Modifications got me to cost-score pareto frontier at $0.00773/Mtok
x.com/matthewagi/status/2113370655957877177采集于 2026.10.23 10:07