Compare commits

...

3 Commits

Author SHA1 Message Date
Daoyuan Li 23dd4c2fa8
Merge 56d4cddfd8 into 7a6fddd63a 2026-08-31 11:11:00 -07:00
jingyaogong 7a6fddd63a [update] readme 2026-08-31 18:08:05 +08:00
jingyaogong c9a8ab4632 [update] dependency version 2026-08-31 17:54:37 +08:00
3 changed files with 6 additions and 2 deletions

View File

@ -1909,6 +1909,8 @@ python llmexport.py --path /path/to/模型路径/ --export mnn --hqq --dst_path
* [@Nijikadesu](https://github.com/Nijikadesu):[🔗以交互笔记本方式分解项目代码](https://github.com/jingyaogong/minimind/issues/213)
* [@jaylearnstocode](https://github.com/jaylearnstocode):[🔗模型结构、注意力机制与训练流程可视化](https://llm-visualization-minimind.vercel.app/)
致谢以下优秀的论文与项目:

View File

@ -1909,6 +1909,8 @@ Thanks to the following contributors for sharing training notes, data processing
* [@Nijikadesu](https://github.com/Nijikadesu): [🔗Breaking Down Project Code in Interactive Notebook Format](https://github.com/jingyaogong/minimind/issues/213)
* [@jaylearnstocode](https://github.com/jaylearnstocode): [🔗Visualization of Model Architecture, Attention Mechanisms, and Training Pipelines](https://llm-visualization-minimind.vercel.app/)
Thanks also to the following papers and projects:

View File

@ -23,10 +23,10 @@ jinja2==3.1.2
jsonlines==4.0.0
trl==0.13.0
ujson==5.1.0
wandb==0.18.3
wandb==0.22.3
streamlit==1.50.0
einops==0.8.1
swanlab==0.7.11
swanlab==0.9.8
modelscope==1.37.0
# torch==2.6.0
# torchvision==0.21.0