chore: improve model not found error msg

[ZiniuYu]

We did not list all available models when the user input a wrong model name in torch runtime previously, this pr fix this
this pr also reformat the error msg, it now looks like

[codecov]

Codecov Report

Merging #812 (78a75a7) into main (ea23968) will increase coverage by 2.25%.
The diff coverage is 66.66%.

@@            Coverage Diff             @@
##             main     #812      +/-   ##
==========================================
+ Coverage   81.65%   83.90%   +2.25%     
==========================================
  Files          21       21              
  Lines        1466     1466              
==========================================
+ Hits         1197     1230      +33     
+ Misses        269      236      -33     

Flag	Coverage Δ
cas	83.90% <66.66%> (+2.25%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
server/clip_server/model/clip_model.py	87.50% <0.00%> (ø)
server/clip_server/model/clip_onnx.py	82.22% <ø> (ø)
server/clip_server/model/clip_trt.py	85.71% <ø> (+16.32%)	⬆️
client/clip_client/__init__.py	100.00% <100.00%> (ø)
server/clip_server/__init__.py	100.00% <100.00%> (ø)
server/clip_server/model/trt_utils.py	83.51% <0.00%> (+27.47%)	⬆️

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

[numb3r3]

What happens on other backend, ONNX and TensorRT

[ZiniuYu]

What happens on other backend, ONNX and TensorRT

the are fine

[ZiniuYu]

@numb3r3 I tried to use f'' strs but python doesn't allow to put backslashes in it, so I have to '{}'.format() instead