Downloads · 30 days
25
5% of all-time downloads
stella_en_400M_v5
GameScribes/stella_en_400M_v5
stella_en_400M_v5 is a machine learning model from GameScribes. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Re-Upload of https://huggingface.co/dunzhang/stellaen400Mv5 with : - Only 1024 embeddings dimensions folder - Max tokens lenght to 512 ( model has been trained on this sequence lenght ) - Padding strategy set to "Batc…
All-time downloads
467
Public
Parameters
435M
1.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 100%
At a glance
- Model type
- new
- Access
- Public
- Created
- Nov 2, 2024
- Updated
- Nov 8, 2024
- SHA
- 5604e1b9
Model card
From the Hugging Face model README
Re-Upload of https://huggingface.co/dunzhang/stella_en_400M_v5 with :
- Only 1024 embeddings dimensions folder
- Max tokens lenght to 512 ( model has been trained on this sequence lenght )
- Padding strategy set to "BatchLongest" to avoid batching every line to a fixed length of 512 tokens in case of size less than 512. Remove unecessary padding.
Parameters at the end of the file "config.json" has been set manually to false for CPU usage:
"unpad_inputs": false, "use_memory_efficient_attention": false
You can turn them back to "true" to enable GPU usage back again
- Type
- new
- Created
- Nov 2, 2024
- Updated
- Nov 8, 2024