The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.
1M Pulls 33 Tags Updated 1 year ago
1,547 Pulls 11 Tags Updated 1 year ago
Bfloat16 version of the Granite3 dense 8B instruct model.
12 Pulls 1 Tag Updated 1 year ago
37 Pulls 1 Tag Updated 1 year ago