GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026
64views this month
Decision brief
xTuring is a Python-based framework for personalizing and fine-tuning open-source language models, offering tools for data pre-processing and fine-tuning.
Good fit when
- Use xTuring when you need to fine-tune open-source LLMs with specific requirements for mixed-precision training or quantization.
- Choose xTuring if you are working with models like GPT-2, GPT-J, or LLaMA and require the use of INT8 or INT4 engines for efficient training.
Avoid when
- Avoid xTuring if your project requires the latest features from transformers 5.x, as xTuring currently supports transformers up to version 4.36.0.
- Do not use xTuring if you are planning to work with Qwen3-Omni, as support for this model is not yet released.
- Requirements:
- xTuring requires transformers version 4.36.0 or higher, but not the 5.x series.; Support for Qwen3-Omni, which requires transformers 5.0.0 or higher, is not yet available.
Observed Sep 18, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (5d since push)
- As of Sep 18, 2026
- Provenance
- Not a fork · Organization account
- As of Sep 18, 2026
- Security (OSV)
- No lockfile
- As of Sep 18, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install xTuringSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Provides tools for data pre-processing and fine-tuning of open-source LLMs
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Sep 18, 2026
- Languages
- python
Source: github.language+pyproject.toml · Sep 18, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
⚙️ Installation Note: xTuring requires . Do not upgrade to 5.x yet — 5.x drops the / loading kwargs that the INT8/INT4 engines rely on, and nothing currently shipped needs 5.x. Qwen3 Omni support (which requires ) is not released yet — see 318. Development Installation If you wan...
For agents
This page has a .md twin and JSON over the API.