Stats
Actions
Tags
From together-pack
Guides performance tuning for Together AI inference, fine-tuning, and model deployment using OpenAI-compatible API. Covers errors, models, batch inference, and resources.
How this skill is triggered — by the user, by Claude, or both
Slash command
/together-pack:together-performance-tuningThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Guidance for performance tuning with Together AI inference and fine-tuning API.
Guidance for performance tuning with Together AI inference and fine-tuning API.
base_url = 'https://api.together.xyz/v1'together Python SDK or any OpenAI client library| Error | Cause | Solution |
|---|---|---|
401 Unauthorized | Invalid API key | Check at api.together.xyz |
Model not found | Wrong model ID | Use client.models.list() |
429 Rate limit | Too many requests | Implement backoff |
500 Server error | Model overloaded | Retry with backoff |
See related Together AI skills for more patterns.
npx claudepluginhub jeremylongshore/claude-code-plugins-plus-skills --plugin together-packGuides Together AI API integration for inference, fine-tuning, and model deployment using OpenAI-compatible clients and Python SDK.
Fine-tune models on Together AI using LoRA, full fine-tuning, DPO, VLM, function-calling, reasoning, and BYOM uploads.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.