Open Models Almanac
Methodspost-trainingmid-training & continual pretraining

methods · post-training

mid-training & continual pretraining

18 methods filed at this node or below it, from the sources of 17 models.

In this branch 18

Everything filed at this node or below it, with one collapsible heading per child node.

filed here 18

Long-context extension via continued pretraining core · 12 sources · 16 quotes
Mid-training core · 5 sources · 6 quotes
Continued pretraining used · 4 sources · 4 quotes
Indic continued pretraining used · 4 sources · 4 quotes
Long-context recovery training used · 4 sources · 6 quotes
Software-engineering mid-training used · 4 sources · 5 quotes
12 single mentions
Agent-centric mid-training used · 1 source · 1 quote
Broad robot-data pretraining used · 1 source · 1 quote
Human-video pretraining used · 1 source · 1 quote
Joint text-and-audio mid-training used · 1 source · 1 quote
Mid-training on the MolmoAct Dataset used · 1 source · 1 quote
Multimodal mid-training used · 1 source · 1 quote
Physical-AI-focused pretraining used · 1 source · 1 quote

By model

Which of this branch's methods each model's own documents describe, and how strongly. Under each model: its strongest treatment anywhere in the branch.

Modelmethods
MiMo-V2.6-Flash usedAgent-centric mid-training usedMid-training alignment data from reward-hacking cases used—
NVIDIA-Nemotron-3-Ultra-550B-A55B usedContinued pretraining usedLong-context extension via continued pretraining used—
Alpamayo 1.5 / 2 Super usedPhysical-AI-focused pretraining used—
DeepSeek-V3.2 usedContinued pretraining used—
DeepSeek-V4-Flash-Vision-Exp coreContinued training for visual understanding core—
DeepSeek-V4-Pro usedMid-training used—
GR00T N1.7 usedHuman-video pretraining used—
Kolibri-1 usedLong-context extension via continued pretraining used—
LFM3-1.7B usedJoint text-and-audio mid-training usedLong-context extension via continued pretraining usedMid-training usedMid-training with lower-quality SFT datasets usedMultimodal mid-training usedContinued pretraining optional—
Laguna-S-2.1 usedLong-context extension via continued pretraining used—
MiMo-V2.6-Pro usedAgent-centric mid-training usedMid-training alignment data from reward-hacking cases used—
MolmoAct 2 coreMid-training coreMid-training on the MolmoAct Dataset used—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B coreLong-context extension via continued pretraining coreMid-training coreIndic continued pretraining usedLong-context recovery training usedSoftware-engineering mid-training used—
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B coreLong-context extension via continued pretraining coreMid-training coreContinued pretraining with natural and synthetic data usedIndic continued pretraining usedLong-context recovery training usedSoftware-engineering mid-training used—
Qwen3.5-397B-A17B usedContinued pretraining used—
VLA Foundry (Foundry-VLA-1.7B) usedSequential LLM-to-VLM-to-VLA training pipeline used—
π0.5 usedBroad robot-data pretraining used—
↑