-
- RNN：序列建模、自然语言处理、机器翻译
- CNN：图像分类、目标检测、语义分割
- Transformer：自然语言处理
- FNN：通用任务
- AE：压缩、去噪、生成
- GAN：图像生成、文本生成、语音生成
- RL：游戏、机器人控制、金融交易
-
Hey!
Cool repo. I like all the knn+lm methods
Did you do some runs yet? Anything interesting to report?
-
i compiled ZLUDA ```Finished `release` profile [optimized] target(s) in 5m 40s```
i dowloaded `nccl` from NVIDIA and placed it inside of the ZLUDA directory
`P:\gitrepos\ZLUDA\nccl_2.21.5-1+cuda11.0…
-
I am following the instructions on the RETRO-pytorch GItHub repo. After training my model, how do I go about using it to generate responses?
```
retro = RETRO(
chunk_size = 64, …
-
Memory use will remain below 2Gb most of the time during training, using the following configuration.
But will soon encounter OOM at **epoch-2, iteration 94**.
`
RuntimeError: CUDA out of memor…
-
This is an excellent work!
When I convert .obj to video, I encounter an issue as below:
…
-
### pycaret version checks
- [X] I have checked that this issue has not already been reported [here](https://github.com/pycaret/pycaret/issues).
- [X] I have confirmed this bug exists on the [latest…
-
-
### Describe the bug
Hi, I have setup the opensearch cluster to run on single instance. I have created the embedding model and setup the pipeline to do the text-embedding on indexing the documents. I…
-
## DINOv1: Emerging Properties in Self-Supervised Vision Transformers
* \[[`blog`](https://ai.facebook.com/blog/dino-paws-computer-vision-with-self-supervised-transformers-and-10x-more-efficient-tr…