Contents:

Continued training for RayExtract-1B-v0.2-iter2 with 1 extra epoch (hopefully further decrease training loss), 5e-5 learning rate, batch size 16

Downloads last month
5
GGUF
Model size
1.24B params
Architecture
llama
Hardware compatibility
Log In to view the estimation

4-bit

5-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support