onnxsim_large_model icon indicating copy to clipboard operation
onnxsim_large_model copied to clipboard

simplify >2GB large onnx model

Results 8 onnxsim_large_model issues
Sort by recently updated
recently updated
newest added

I tried to simplify TinyLlama with the code, but the simplified onnx file is almost with the same size with non-simplified one. It is appreciated if you can provide onnx...

![微信截图_20240222192343](https://github.com/luchangli03/onnxsim_large_model/assets/12314280/20bccc9b-b247-4826-8919-0db8db690c2a)

python simplify_large_onnx.py -m my.onnx --save_extern_data 0 --skip 0 compress model success simplify model success ` uncompress model success Traceback (most recent call last): File "simplify_large_onnx.py", line 60, in simplify_large_onnx(args) File...

onnx模型很小,但是netron打开还是警告模型太大,打开缓慢

error log: ``` onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Type Error: Type parameter (T) of Optype (MatMul) bound to different types (tensor(float16) and tensor(float) in node (/layers.0/self_attn/k_proj/MatMul). ```

我看32k和原生的模型结构基本是一致的,尝试了一下导出,没有问题,但是无法正确推理,推理到onnx计算部分就直接Killed退出了,请问这是什么原因?请问作者可以支持一下32k的推理吗?我这边想试试把模型导出为rknn架构。

Hi ~ I use the tool to simple GPT-3 large。i get the error ~ please help,thx! FileNotFoundError: [Errno 2] No such file or directory: '/home/young.ruan/onnxsim_large_model/simple_onnx/349fb200-3fc2-11ee-81a6-bc224705bc66' ![image](https://github.com/luchangli03/onnxsim_large_model/assets/8943172/bb4a0b39-9336-453e-bdd5-6ad80f1b82e8)