Nikolay Maslovich

Add on-the-fly sampling

2

As far as I understand, right now text pairs are picked directly using Datapack samples. However it is almost impossible to mine "hard" negative samples before training. Just adding into...

I have a task in which I need to match several texts with huge (~1M texts) database. Even though available models are pretty fast, this is not enough. The best...

In this merge I: - added `port` (optional) parameter to main script and `webdriver` call - commented out `get_response` call, because it does not work - increased timeout so in...

Just watched your video and found interesting to improve your CrossOver function. https://github.com/lebionick/CrossOver here's the link for my git, it is in Java and there's some excess code, but I...

✨[Feature] add working unified example INT8 quantization and compilation

1

I would like to quantize my model to INT8 precision and then compile it using torch_tensorrt. Unfortunately, it is [transformer based vision model](https://github.com/mit-han-lab/efficientvit/blob/master/efficientvit/models/efficientvit/seg.py#L264) and default way to do it -...