Jasper

extract_data input_module kwarg accepts strings

1

I think it makes sense to modify `extract_data` to accept strings as the canonical `input_module` kwarg, as it saves the user from having to instantiate their own `input_module`. (Especially because...

Hey guys! I gave an image_to_spectrogram implementation a go of it, seems to work from what I can tell. Implemented this to allow for style transfer on custom-uploaded audio :)

Add example: improving embeddings sequences with lowpass filtering

4

Hey team - here's an example notebook for using signal processing methods to improve the OpenAI embeddings' ability to encode long documents. Full paper can be found here: https://jagilley.github.io/fft-embed.html Let...

I thought it'd be fun to add functionality for automatically generating a token graph from the `TokenTrie` class, sort of like the one in the original LLaMPPL paper! A screenshot...

Could you provide an example of how to use `Model.twist()`? Currently, I'm calling it in `step()` with values between 0 and 1. I'd imagine that the effect size should be...

Getting an error when attempting to finetune Mixtral

2

``` Traceback (most recent call last): File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/workspace/mistral-finetune/utils/validate_data.py", line 366, in main(args)...

Cannot use wandb logging

3

getting ``` root@05dcba51026c:/workspace/mistral-finetune# torchrun --nproc-per-node 2 --master_port $RANDOM -m train config.yaml [2024-05-29 00:06:22,437] torch.distributed.run: [WARNING] [2024-05-29 00:06:22,437] torch.distributed.run: [WARNING] ***************************************** [2024-05-29 00:06:22,437] torch.distributed.run: [WARNING] Setting OMP_NUM_THREADS environment variable for each...