fix review findings and additional clean up

[iamleonie]

• Addressed post-merge review feedback on the migration guide.
• Simplified runtime guidance into GPU inference and edge/on-device deployment links. (Didn't contain much migration specific details)
• Reworked migration guide sections for clearer navigation: Deployment runtimes, Chat Template, Sampling Configuration, Tool Use, and Fine-tuning.
• Added section-level links from the intro and moved main documentation references to the bottom of each section.
• Clarified sampling guidance and linked to the Prompting Guide for per-model recommendations.
• Standardized tool-use guidance around the lfm2 parser and native Pythonic tool-call format. (confirmed its called lfm2 parser
• Added reusable snippets for shared ChatML and tool-call examples.
• Removed duplicated fine-tuning stack details and linked to the canonical fine-tuning docs.

[mintlify]

Preview deployment for your docs. Learn more about Mintlify Previews.

Project	Status	Preview	Updated (UTC)
liquid-docs	🟢 Ready	View Preview	Jul 10, 2026, 3:38 PM

💡 Tip: Enable Workflows to automatically generate PRs for you.

[mlabonne]

I noticed that we're talking about Qwen3 and Gemma 3 instead of Qwen3.5 and Gemma 4 everywhere. We should probably either update it when there's a clear replacement or have both when there's none (particularly true for Gemma 4).

[iamleonie]

to reduce maintenance efforts for the future, i decided to remove all direct model IDs and replace them with more generic categories.