-
I installed via conda, python 3.9, cuda 11.3 pytorch 1.11
but when I try to use ngp I get this error, not sure how to fix, any help would be very appreciated
(torch-ngp) C:\torch-ngp>python mai…
-
Hello, I am looking for a way to forward propagation of `Mask2Former` using `EncoderDecoder`.
However, I get an error that there are not enough arguments for `forward` of `decoder_head`.
sample co…
-
#28 tracks the issue where some native node_modules are not detected as files that should be signed, so the workaround is:
- Sign bundle: `sign Foo.app`, then `notary-submit`
- For every file in the…
-
Elegant work! In addition to training a transformer_base-scale model, I am still trying to train a large model, (e.g., 1024 model dim. & 4096 hidden dim), such that I can fine-tune Mask-predict with […
-
Thanks a lot for creating Gumbi. I was playing around a bit with it and I hope it will evolve further!
What I was trying to do is actually explained here: https://discourse.pymc.io/t/use-exact-gaussi…
-
when executing inference.py with
arch = 'TinyCLIP-auto-ViT-63M-32-Text-31M'
model, _, preprocess = open_clip.create_model_and_transforms(arch, pretrained='LAIONYFCC400M')
an error occurs:
Mis…
-
`loek@DORAEMON:~/modernmt4$ ./mmt create zh en data/proceng -e proceng --gpus 0 --resume
=========== TRAINING STARTED ===========
ENGINE: proceng
LANGUAGE: zh > en
(1/4) Cleaning corpora
…
-
非常抱歉在这个时刻打扰到你，很荣幸阅读你的论文，从中受到了很多启发。但是我在使用你的源码去实验的过程中遇见了一些问题，希望能请教一下你。在使用validation_realWorld.py时遇见了这样的问题，不知道该怎么样解决。
Traceback (most recent call last):
File "D:\End-to-end-DRL-for-FJSP-main\FJSP_Rea…
ghost updated
7 months ago
-
## 🚀 Feature
Improved Transformer and MultiHeadAttention design
## Motivation
Current Transformer and MultiHeadAttention design is not a very `PyTorch`-ish. The `in_proj` is not even a `nn.Mo…
-
### 🚀 The feature, motivation and pitch
I'm trying to write an inductor lowering for `torch._cslt_sparse_mm`, an aten op that takes has two optional tensor kwargs, `bias` and `alpha`.
https://git…
jcaip updated
2 weeks ago