-
Trying to test the prediction with the minimal code from
https://github.com/marcopeix/time-series-analysis/blob/master/lag_llama.ipynb
https://medium.com/@odhitom09/lag-llama-an-open-source-base-m…
-
https://github.com/pytorch/vision/actions/runs/5941974400/job/16117254380
Failures start with 9c4f7389d0db7cfe7e8591ea920459673344aaa8, which is the first commit that used yesterdays (20230822) PyT…
-
I would like to finetune BERT (or similar) models for an asymmetric task using two different embeddings. There will be two inputs (1 and 2), and I would use an embedding in 1 and an embedding in 2 to …
-
## ❓ Questions and Help
I have noticed during testing that enabling FSDP's flatten_parameter=True results in a significant increase in GPU Peak Memory. In fact, the memory usage is several times la…
-
Hi, I'm grateful for your excellent work! I've implemented the code as per the instructions, and it runs without errors. However, the inference time is slow, approximately 176 seconds per iteration. I…
-
# URL
- https://arxiv.org/abs//2305.13048
# Affiliations
- Bo Peng, N/A
- Eric Alcaide, N/A
- Quentin Anthony, N/A
- Alon Albalak, N/A
- Samuel Arcadinho, N/A
- Huanqi Cao, N/A
- Xin Che…
-
As the title says, is there any way to add the evaluation script for the transliteration task. I am currently working on creation of a transliteration dataset and training a neural model on the extrac…
-
буду хранить тут дамп статей про трансформеры, которые читаю, либо которые хочу прочитать
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale - статья где предложили ViT, иде…
-
### What would your feature do ?
I'm developing an extension and discovered something strange in the configuration with the CLIPTokenizer on Automatic1111 for an SDXL model i downloaded from civita…
-
## 🚀 Feature
Update weight initialisations to current best practices.
## Motivation
The current weight initialisations for a lot of modules (e.g. `nn.Linear`) may be ad-hoc/carried over from Torc…