Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
大语言模型微调，Qwen2VL、Qwen2、GLM4指令微调
| Date | Stars |
|---|---|
| 2026-07-31 | 653 |
| 2026-08-01 | 652 |
| 2026-08-06 | 652 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# LLM Finetune 实验细节看： [](https://swanlab.cn/@ZeyiLin/Qwen2-fintune/runs/cfg5f8dzkp6vouxzaxlx6/chart) [](https://swanlab.cn/@ZeyiLin/GLM4-fintune/runs/eabll3xug8orsxzjy4yu4/chart) [](https://swanlab.cn/@ZeyiLin/Qwen2-VL-finetune/runs/pkgest5xhdn3ukpdy6kv5/chart) ## News - [Qwen3-Medical-sft](https://github.com/Zeyi-Lin/Qwen3-Medical-SFT): Qwen3微调实战：医疗R1推理风格聊天 ## 准备工作 安装环境：`pip install -r requirements.txt` 文本分类任务-数据集下载：在[huangjintao/zh_cls_fudan-news](https://modelscope.cn/datasets/swift/zh_cls_fudan-news/files)下载`train.jsonl`和`test.jsonl`到根目录下。 命名实体识别任务-数据集下载：在[qgyd2021/chinese_ner_sft](https://huggingface.co/datasets/qgyd2021/chinese_ner_sft/tree/main/data)下载`ccfbdci.jsonl`到根目录下。 Qwen2-VL多模态任务-数据集下载： ```bash cd ./qwen2_vl python data2csv.py python csv2json.py ``` ## 训练 | 模型 | 任务 | 运行命令 | Notebook | 文章 | | ---------- | ----------------- | -------------------------------------------------------------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | | Qwen2-VL-2b | 多模态微调 | 进入qwen2_vl目录，运行python train_qwen2_vl.py | wait | [知乎](https://zhuanlan.zhihu.com/p/702491999) | | Qwen2-1.5b | 指令微调-文本分类 | python train_qwen2.py | [Jupyter Notebook](notebook/train_qwen2.ipynb) | [知乎](https://zhuanlan.zhihu.com/p/702491999) | | Qwen2-1.5b | 指令微调-命名实体识别 | python train_qwen2_ner.py | [Jupyter Notebook](notebook/train_qwen2_ner.ipynb) | [知乎](https://zhuanlan.zhihu.com/p/704463319) | | GLM4-9b | 指令微调-文本分类 | python train_glm4.py | [Jupyter Notebook](notebook/train_glm4.ipynb) | [知乎](https://zhuanlan.zhihu.com/p/702608991) | | GLM4-9b | 指令微调-命名实体识别 | python train_glm4_ner.py | [Jupyter Notebook](notebook/train_glm4_ner.ipynb) | [知乎](https://zhuanlan.zhihu.com/p/704719982) | ## 推理 Qwen2系列： ```bash python predict_qwen2.py ``` Qwen2-VL系列： ```bash cd ./qwen2_vl python predict_qwen2_vl.py ``` GLM4系列： ```bash python predict_glm4.py ``` ## 引用工具 - [SwanLab](https://github.com/SwanHubX/SwanLab)：AI训练记录、分析与可视化工具
Excerpt of 2,376 characters
Read on GitHub
Ze-Yi LIN · Emotion Machine Lab · China
30
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3a82af15920222b2, name:finetune