Timothy Lim

Update regnet.py

6

## Motivation In the example comment to print out the different layers of outputs, we need to indicate the `out_indices` to (0,1,2,3) to see all backbone layers output as the...

[Docker: Cannot Build TensorRT Plugin]- No CUDA runtime is found

9

Hi, I have search the issues and it seems that there are no solutions to get mmcv with tensorrrt plugin build in Docker. Dockerfile: ``` FROM nvcr.io/nvidia/tensorrt:20.12-py3 . # all...

[FEATURE] Creating Scheduler V2 (same as create_optimizer_v2 concept)

2

When building optimizers now, we can use the function `create_optimizer_v2` to take in keyword arguments instead of the parser arguments. This makes it easier to set up configuration files (can...

runnable code

Why did you decided to use GPT instead of BERT for extractive Q/A?

1

It seems to me that nearly all extractive Q/A models are based in encoder/encoder-decoder networks, were there any particular reason to use a generative decoder network instead for this task?...

I been trying to use GPT2-1.5b to do some Q/A but it seems that the model continues to generate (repeating itself over and over again) until max tokens are reached....

Are there any particular reason for using `### ` for instruction, input and response?

4

I know that in markdown format `### ` is treated as section/subsection title. Are there any relevance there? Edit to make the question clearer: In the training script, the inputs...

Why proceed with this kind of research evaluation process?

1

Please correct me if I got anything wrong. I am trying to learn more about LLM research. Alpaca Contribution: Your research team instruction tuned llama via the self-instruct method and...

Can we load locally?

2

I tried downloading the `.json` file from lottie and putting it into `st.lottie("path/to/json")` but it does nto work.

Allow `model_validate_json` to return valid JSON string upon raising error

6

### Initial Checks - [X] I have searched Google & GitHub for similar requests and couldn't find anything - [X] I have read and followed [the docs](https://docs.pydantic.dev) and still think...