decoder_model_merged invalid model error for FP16 and Q4F16

#7
by selimarikan - opened

Hi, thanks for providing tons of quants and models here, much appreciated!
For fp32 everything is working great.

However, when I try to load decoder_model_merged_fp16 or decoder_model_merged_q4f16 I am getting the following error:

[ONNXRuntimeError] : 1 : FAIL : Load model from .. failed:/onnxruntime_src/onnxruntime/core/graph/graph.cc:1489 void onnxruntime::Graph::InitializeStateFromModelFileGraphProto() 
This is an invalid model. Subgraph output (logits) is an outer scope value being returned directly. 
Please update the model to add an Identity node between the outer scope value and the subgraph output.

Sign up or log in to comment