William

I clone the repo and npm run myself, and it works (But I didn't change the GITHUB_ID and GITHUB_TOKEN in `.env` to mine). And I see the commit badge in...

> Are you using the KDE version of Manjaro, by chance? I have consistently run into this error on a variety of packages, including terminalizer. same (using Manjaro KDE)

Support backward of middle hidden states by PR #40 .

have you tried something like tutorial/2.1_conditional_generation.py?

For finetune, refer to https://github.com/OpenBMB/ModelCenter/tree/main/model_center/dataset/t5dataset. For pretrain, refer to https://modelcenter.readthedocs.io/en/latest/notes/pretrain_data.html.

It might be that the phone's GPU is relatively old, since the current deployment framework utilizes the GPU. We are working to shift our deployment framework to that uses the...

理论上支持，可以直接安装我们的 APK 测试 (https://github.com/OpenBMB/mlc-MiniCPM/?tab=readme-ov-file#android-apk) 另外上面提到的基于 CPU 的框架 llama.cpp 的适配我们已经跑通 (https://github.com/ggerganov/llama.cpp/pull/6919)

Probably related to https://stackoverflow.com/questions/33314169/numerous-connectionrefusederror-winerror-10061-in-python-requests

看上去和 mlc-ai-nightly 版本有关，我本地里 https://github.com/mlc-ai/relax/blob/mlc/python/tvm/relax/frontend/nn/_tensor_op.py 这个接口对应的代码为 （我使用的版本为 0.12.dev1953） ```python def reshape(self, shape): return _op().reshape(self, shape) ``` 而新版已经改为 ```python def reshape(self, *shape): return _op().reshape(self, shape) ``` 这个修改发生在最近一个月中：https://github.com/mlc-ai/relax/commit/0b13b5c8445dfae5718af13faafef942d0a607fa

可能和这个有关 https://github.com/mlc-ai/mlc-llm/issues/665 ，怀疑和模型无响应（例如手机内存不足）有关