Add detailed error messaging for reading/writing of model files.

[Ghatage]

I was trying to quantize a gptj model and the code failed to quantize it.
I was wondering what the problem was since the error message wasn't very detailed and the help message of the converters weren't very detailed either.

I followed some steps mentioned here: #32 (comment)
Turns out the convert code needs an output directory but the quantize code needs the absolute path to the file name and not an output directory.

So I added some detailed error messaging to clarify that. Now it prints the error code:

~/code/oss/cformers/cformers/cpp > ./quantize_gptj ~/.cformers/models/gptj/modelOne/modelOne-f32.bin . 2
gptj_model_quantize: loading model from '/Users/aghatage/.cformers/models/gptj/modelOne/modelOne-f32.bin'
gptj_model_quantize: failed to open '/Users/aghatage/.cformers/models/gptj/modelOne/modelOne-f32.bin' for reading: No such file or directory
main: failed to quantize model from '/Users/aghatage/.cformers/models/gptj/modelOne/modelOne-f32.bin'