#Ember-1
5 stories · 0 in 7 days · 0 in 30 days
Stories, products and papers tagged "Ember-1", newest first.
Oct 1
Sep 28
Chinese contentFireworks 推出 Ember-1：基于 Kimi K3，推理 token 用量减少约 40%
Fireworks 拿 Kimi K3 改了个 Ember-1，推理 token 少用 40% 还不掉分，省钱党可以看看。
Fireworks Ember-1 cuts Kimi K3 token use by ~40%
Token waste in agentic loops is one of the biggest hidden costs of running reasoning models, and post-training on real task loops offers a cheaper fix than prompt tricks or output caps. Teams building coding agents on K3 or similar models can cut inference spend materially without dropping success rates. Fireworks is US-based but the base model is Moonshot (Kimi)'s K3, a useful data point in the open-model cost race.
Chinese contentSebastian Raschka 简评 Ember-1：靠后训练打造前沿模型
Raschka 简评了 Ember-1，还顺带说了句实在话：小预算做前沿模型，与其从头训练，不如把钱花在后训练上。
Sep 24
Chinese contentFireworks 发布 Ember-1：基于 Kimi K3 减少 40% 推理 token
Fireworks 在 Kimi K3 上做了个减法：推理 token 少用 40% 但质量不掉，跑推理烧钱的朋友可以看看。