tao-finetune-cosmos-reason
by NVIDIA
Cosmos-Reason2-8B video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video question-answering models, fine-tuning Cosmos-Reason2 with SFT, or working with Cosmos-RL. Trigger phrases include "fine-tune Cosmos-Reason", "Cosmos-RL SFT", "video QA fine-tune", "Cosmos-Reason2-8B training".
Description
1
Installs
Install tao-finetune-cosmos-reason with One Click
Get a managed OpenClaw server and install this skill from your dashboard. No SSH, no Docker, no configuration needed.
Deploy with ClawHost