Migrating to Unsloth v0.1.49-beta
Version v0.1.49-beta introduces 2 breaking changes. This guide details how to update your code.
Released: 7/15/2026
⚠️ Check Your Code
If you use any of these symbols, you need to read this guide:
llama.cppAGENTS.mdCLAUDE.mdtorch.compiletransformersCONFIG_MAPPING_NAMESInklingQwen3.6 35BQwen3.6 27BQwen3.5 122BGLM-4.7 FlashGemma 4DeepSeek-V4SyntheticDataKit.chunk_datasmart_chunk_textFastSentenceTransformertorchaoMCPClaude CodeAnthropicBreaking Changes
●Issue #1
Removed `AGENTS.md` / `CLAUDE.md` from install artifacts and tightened instruction-file cleanup. Users may need to manually re-add or manage these files if they were relying on them being present in the installation.
●Issue #2
Stopped silent full-sequence training: 'Train on completions' used a hardcoded template table and silently disabled masking on a miss. This change means DeepSeek and most LFM models trained on prompts too while the toggle said otherwise. Markers are now auto-detected from the tokenizer's chat template, and manual response-template markers that never matched their rendered templates have been fixed. This might affect training behavior if relying on the previous silent masking.
Migration Steps
- 1If relying on `AGENTS.md` or `CLAUDE.md` being present in install artifacts, manually re-add or manage these files.
- 2Users training models may need to review their training configurations due to changes in how markers are auto-detected from tokenizer chat templates and fixes to manual response-template markers.
Release Summary
Unsloth introduces extensive customization for its Studio, including new color palettes, custom fonts, and seven new display languages. Agents are now safer with enhanced tool-call permissions and workspace isolation, while Intel GPUs gain GPU-accelerated inference via Vulkan `llama.cpp` support.
Need More Details?
View the full release notes and all changes for Unsloth v0.1.49-beta.
View Full Changelog