allenhung1025

It seemed that the generator architecture is different from your paper. The implementation of Generator consists of a series of upsamplings, and then a series of residual blocks. However, in...

make loss.backward() work

1

I was trying to use gumbel_intersection in my training code. However, when calling the loss.backward(), there would be an error message. [Imgur](https://i.imgur.com/0AD09W6.png) which shows that there should not be an...

BELLE-LLaMA-EXT-7B 模型md5不一致

1

md5不一致 https://huggingface.co/BelleGroup/BELLE-LLaMA-EXT-7B 下载后pytorch_model-00001-of-00002.bin.3b0666c50d7fd55d5116e788ec51aa96a34ba6816e86ffbee1dbe983bf511b4b.enc的md5sum和官网上的不一致 想请问如何解决

cannot find webq json files

1

https://github.com/DevSinghSachan/art/blob/f86535c2ac5efeb364d7e6f2567a60a684a6df19/examples/supervised-retriever-training/mss_dpr_nq.sh#LL20C1-L23C37 I cannot find JSON files after running the download data script `examples/helper-scripts/download_data.sh` Where can I find those files? Thank you in advance.

`merge_lora` should be changed to `merge_adapter`, so the code could be run successfully.

What does blur function do?

3

Dear author: Thanks for your amazing repo, it helped me understanding stylegan more. I got stuck when tracing your code at model.py I didn't understand what blur functions do and...

The tutorial for https://github.com/replicate/cog/blob/main/docs/getting-started.md can not do for M1 Mac, so modified from tensorflow to pytorch. Related issue - https://github.com/replicate/cog/issues/336

[The testing result on a siren audio file seems not working from my end]

2

Hi @RetroCirce , I want to thank you for your great work!!!! I am playing around the model checkpoint you provided (`HTSAT_AudioSet_Saved_6.ckpt`). I can successfully load the model checkpoint and...

add cog quick inference

1

1. Can run the pre-trained model `HTSAT_AudioSet_Saved_1.ckpt` real quick without building the environment and messing around the code. 2. add `cog.yaml` and `predict.py` 3. update the `README.md`