Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm criteria.
26.6K Pulls 16 Tags Updated 3 months ago
The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.
339.5K Pulls 10 Tags Updated 1 year ago
(draft) The IBM Granite Guardian 3.1 2B and 8B models are designed to detect risks in prompts and/or responses.
151 Pulls 3 Tags Updated 1 year ago
324 Pulls 16 Tags Updated 3 months ago
24 Pulls 2 Tags Updated 4 months ago
8 Pulls 16 Tags Updated 3 months ago
4 Pulls 1 Tag Updated 3 months ago
1,447 Pulls 6 Tags Updated 1 year ago
887 Pulls 12 Tags Updated 1 year ago
141 Pulls 14 Tags Updated 1 year ago
87 Pulls 12 Tags Updated 1 year ago
27 Pulls 12 Tags Updated 1 year ago
10 Pulls 12 Tags Updated 1 year ago
10 Pulls 1 Tag Updated 1 year ago
4 Pulls 2 Tags Updated 1 year ago
1 Pull 12 Tags Updated 1 year ago
12 Tags Updated 1 year ago