should have the ability to output debug artifacts when exporting to a .pte file

### 🚀 The feature, motivation and pitch

should be able to use --generate_etrecord to get the artifacts for debugging like this. 
`python3 torchchat.py export llama3.1 --quantize torchchat/quant_config/mobile.json --output-pte-path llama3.1.pte --generate_etrecord`

### Alternatives

_No response_

### Additional context

_No response_

### RFC (Optional)

_No response_