You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
20:33:30.302 MNNJNI E outputIndexesMap:
20:33:30.302 MNNJNI E outputs:
20:33:30.302 MNNJNI E [ sentence_embeddings ]
20:33:30.302 MNNJNI E PipelineModule:: Can't find enough output from the model, finded is:
请问应该如何解决?
The text was updated successfully, but these errors were encountered:
你好,我尝试使用Qwen2.5-0.5B-Instruct + MNN 进行文本向量化。【不定长度文本通过嵌入层转为固定长度向量】
我注意到llm.cpp中的Embedding类,并尝试使用这个进行文本向量化
代码运行到
auto mp = Module::load(
{"input_ids", "attention_mask", "position_ids"},
{"sentence_embeddings"}, model_path.c_str(), runtime_manager_, &module_config);
报错,似乎是因为找不到“sentence_embeddings”层。
20:33:30.302 MNNJNI E outputIndexesMap:
20:33:30.302 MNNJNI E outputs:
20:33:30.302 MNNJNI E [ sentence_embeddings ]
20:33:30.302 MNNJNI E PipelineModule:: Can't find enough output from the model, finded is:
请问应该如何解决?
The text was updated successfully, but these errors were encountered: