Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

failed to convert glm-edge-v-5b to intel openvino model #14

Open
1 of 2 tasks
zutuanwang opened this issue Dec 30, 2024 · 0 comments
Open
1 of 2 tasks

failed to convert glm-edge-v-5b to intel openvino model #14

zutuanwang opened this issue Dec 30, 2024 · 0 comments
Assignees

Comments

@zutuanwang
Copy link

System Info / 系統信息

glm-edge-v-5b, dowload from model.cn

Who can help? / 谁可以帮助到您?

No response

Information / 问题信息

  • The official example scripts / 官方的示例脚本
  • My own modified scripts / 我自己修改的脚本和任务

Reproduction / 复现过程

failed to convert glm-edge-v-5b to intel openvino model:
python convert.py --model_id C:/Users/xxx/.cache/modelscope/hub/ZhipuAI/glm-edge-v-5b --output D:/LLM/glm-edge.openvino/model/glm-edge-v-5b-ov
INFO:nncf:NNCF initialized successfully. Supported frameworks detected: torch, onnx, openvino ⌛ glm-edge-v-5b conversion started. Be patient, it may takes some time. ⌛ Load Original model INFO:nncf:NNCF initialized successfully. Supported frameworks detected: torch, onnx, openvino Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:07<00:00, 3.88s/it] ✅ Original model successfully loaded ⌛ Convert Language model Traceback (most recent call last): File "D:\LLM\glm-edge.openvino\glm-edge-v\convert.py", line 49, in <module> convert_glmv_model(model_path, ir_model_path, compression_configuration) File "D:\LLM\glm-edge.openvino\glm-edge-v\glmv_helper.py", line 319, in convert_glmv_model pkv = model.model( ^^^^^^^^^^^^ File "C:\Users\xxx\.conda\envs\glm-edge-openvino\Lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\.conda\envs\glm-edge-openvino\Lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\xxx\.cache\huggingface\modules\transformers_modules\glm-edge-v-5b\modeling_glm.py", line 775, in forward imgs = torch.unsqueeze(images[0], 0) ~~~~~~^^^ TypeError: 'NoneType' object is not subscriptable

Expected behavior / 期待表现

succeed to convert glm-edge-v-5b to intel openvino model

@zRzRzRzRzRzRzR zRzRzRzRzRzRzR self-assigned this Jan 3, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants