modelscope / modelscope/ms-swift
Support numind/NuExtract3
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
Checklist / 检查清单
- I have searched existing issues, and this is a new feature request. / 我已经搜索过现有的 issues，确认这是一个新的 Feature Request。
Feature Request Description / Feature Request 描述
Checklist / 检查清单
Feature Request Description / Feature Request 描述
Please add support for fine-tuning NuExtract3 from NuMind.
NuExtract3 is a 4B vision-language model based on Qwen3.5-4B (qwen3_5 architecture) specialized for structured information extraction and document-to-Markdown conversion. It supports text, image, and multimodal inputs, and is useful for SFT on document understanding tasks (invoices, receipts, forms, contracts, etc.).
- ModelScope: https://www.modelscope.ai/models/numind/NuExtract3
- HuggingFace: https://huggingface.co/numind/NuExtract3
Pull Request / Pull Request 信息
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Read the NuExtract3 ModelScope and Hugging Face model pages first, focusing on its qwen3_5 architecture and text, image, and multimodal inputs. Compare existing multimodal model integrations in ms-swift, then verify that fine-tuning supports NuExtract3 for structured extraction and document-to-Markdown tasks.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 40/100