Run PyTorch training across GPUs with minimal changes.
Security grade of this SKILL.md: SAFE · how we grade
How to install accelerate
npx skills add NousResearch/hermes-agent --skill accelerate -a claude-code
The skills CLI copies this one skill into Claude Code (use -a for another agent). Or read its SKILL.md on GitHub.
What the SKILL.md says
Accelerate simplifies distributed training to 4 lines of code. Installation: Convert PyTorch script (4 lines): Run (single command): Original script: With Accelerate (4 lines added): Configure (interactive): Questions: Which machine? (single/multi GPU/TPU/CPU). How many machines? (1). Mixed precision? (no/fp16/bf16/fp8). DeepSpeed? (no/yes). Launch (works on any setup): Enable FP16/BF16: Enable DeepSpeed ZeRO-2 (pass a DeepSpeedPlugin, not a raw dict): Or point at a full DeepSpeed JSON config via the plugin: ds_config.json (a raw DeepSpeed config — passed via the plugin, NOT via --config_file): Or via interactive config: Launch (--config_file expects an accelerate YAML, not a raw DeepSpeed JSON): Enable FSDP: Or via config: Accumulate gradients: Effective batch size: batch_size num_gpus gradient_accumulation_steps Use Accelerate when: Want simplest distributed training.
Other skills in NousResearch/hermes-agent
1passwordSet up op CLI, sign in, and read or inject secrets.
3-statement-modelBuild integrated IS/BS/CF financial workbooks in Excel.
actual-setupSet up Actual Computer (actual.inc) inference in Hermes.
adversarial-ux-testRoleplay a hostile user to find and triage UX pain points.