The is the base for finetuning and reinforcement learning. Not intended for general use as its just slower and larger than the original model for now.

It includes a change for more active experts per token (increased top-k) and adjustment of the python code to work for training and transformers 5.

Downloads last month
7
Safetensors
Model size
8B params
Tensor type
BF16
·
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for krampenschiesser/ling3-tiny-base

Finetuned
(9)
this model