This Jamba model has been pruned to just 1B parameters. It was then trained on the first 50k examples of the Ultra Interact Pair dataset for Instruction based fine-tuning.
Initial tests work but may be inconsistent. More info and examples will be posted later
Training
50k Examples
6 hours x A100
Downloads last month
91
Safetensors
Model size
1.02B params
Tensor type
F32
·
Finetuned from
Dataset used to train
Severian/Jamba-UltraInteract-Instruct-1B
Collection including
Severian/Jamba-UltraInteract-Instruct-1B
