Update conversion script versions (#1204)
* Update conversion script versions
* Use custom float16 converter script
* Add MIT license header
* Use relative import
* Fix transformers to stable 4.48.x branch
* Add strictness check when saving model
* Create new output nodes after casts
* Use onnxslim after fp16 conversion
* Prevent in-place modification while iterating (infinite loops)
* Finalize fp16 quantization script
* Only warn if alignment heads can't be found
