-
### 🚀 The feature, motivation and pitch
Contrastive Decoding (Li et al., 2022) is a decoding strategy that contrasts the log probabilities of two or more models at each token to shift the token dis…
-
https://arxiv.org/abs/1703.00955
-
https://virtual2023.aclweb.org/paper_P2296.html
-
i saw the issue with chatglm2-6b.
it run successfully if with numactl -m 0 -C 0-23.
it run failed if with numactl -m 0 -C 0-31, or 0-47 , or 0-55.
i can be reproduced with INT8_ASYM or 4BIT_…
-
# URL
- https://arxiv.org/abs/2304.14293
# Affiliations
- Wangchunshu Zhou, N/A
- Yuchen Eleanor Jiang, N/A
- Ethan Wilcox, N/A
- Ryan Cotterell, N/A
- Mrinmaya Sachan, N/A
# Abstract
- La…
-
Currently in `cli.rs` / `main.rs` the code is using the number of cores detected to determine how many threads to spawn. This is incompatible with using `systemd-run` to limit the CPU resources to max…
-
https://virtual2023.aclweb.org/paper_P5680.html
-
Deck has a cartesian basis on top left, I think :)
If I can change that cartesian basis to be top right, maybe I can easily make deck to LTR and RTL.
This would mean all Decks can work for all c…
-
The following problem is encountered when running your code:
```
Traceback (most recent call last):
File "/home/syrup274/toward-controlled-generation-of-text-pytorch-master/train.py", line 113, i…
-
I notice there are two backpropagations for the generator and encoder.
https://github.com/wiseodd/controlled-text-generation/blob/master/train_discriminator.py#L120-L122
https://github.com/wiseodd…