Downloads · 30 days
13
4% of all-time downloads
CATIE-AQ/FAT5-xl-flan-en
FAT5-xl-flan-en is a feature extraction model from CATIE-AQ. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.
Adaptation of the flan-t5-xl weights to make it compatible with the FAT5 framework (Flash Attention T5). This adaptation should enable the user to efficiently continue the pre-training of the flan-t5 to adapt it to mo…
Downloads · 30 days
13
4% of all-time downloads
All-time downloads
345
Public
Repo size
11.4 GB
Likes
0
Public
Click a slice to open those files.
.safetensors11.4 GB · 100%
From the Hugging Face model README
Adaptation of the flan-t5-xl weights to make it compatible with the FAT5 framework (Flash Attention T5).
This adaptation should enable the user to efficiently continue the pre-training of the flan-t5 to adapt it to more recent data, or to specialize it in a specific domain, for example.
[!WARNING]
For this FAT5-xl-flan-en, we forgot to add a file that is necessary for the model to run (and which we have since lost) 🙃
Thanks to Thalesian for proposing a solution to this problem. We invite you to read his message here to run his fix.
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("CATIE-AQ/FAT5-xl-flan-en", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-xl")