-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
1. install reformer-pytorch from https://github.com/lucidrains/reformer-pytorch
2. install transformers
3. Run script
```pyth…
-
I can see the configure.ac file on the project, but I think it also needs the configure file to run the demo.
mcoto updated
9 years ago
-
# URL
- https://arxiv.org/abs/2309.07124
# Affiliations
- Yuhui Li, N/A
- Fangyun Wei, N/A
- Jinjing Zhao, N/A
- Chao Zhang, N/A
- Hongyang Zhang, N/A
# Abstract
- Large language models (L…
-
加载visualglm模型的时候报错：
For torch.distributed users or loading model parallel models, set environment variables RANK, WORLD_SIZE and LOCAL_RANK.
Traceback (most recent call last):
File "/root/TransGP…
-
As title indicates I'd be interested in understanding whether this is just for text-generation or whether it could also be used to expose the embedding function?
-
Hi, authors. It is an interesting work. But I am confused about the setting of the work. Previous audio generation models, like AudioGen, usually follow the evaluation protocols to generate 10s audio …
-
Hello, the performance of the tokenizer is impressive. I'm particularly interested in the development of the auto-regressive generative model that is being trained with the MagVitV2 tokenizer. I belie…
-
- [ ] [HuggingChat](https://huggingface.co/chat/privacy)
# HuggingChat
**Description:** HuggingChat New Chat This week Model selection iDoDid Theme Models 7 Assistants New Settings About & Privacy …
-
It is currently not possible to script the FlashAttentionFunc layer. It is possible to use a traced model within the same session, but saving the traced model to a file and loading it will also fail w…
-
### 🚀 The feature, motivation and pitch
[Parallel/Jacobi decoding](https://arxiv.org/abs/2305.10427) improves inference efficiency by breaking the sequential nature of conventional auto-regressive …