ibm-granite/granite-guardian-3.2-8b-factuality-detection

Full fine-tune vs ibm-granite/granite-3.2-8b-instruct. Fine-tune: 99% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 72/81, MLP 120/120, Attention 149/160

2 derivatives checked

• mradermacher/granite-guardian-3.2-8b-factuality-detection-i1-GGUF: Quantization
• mradermacher/granite-guardian-3.2-8b-factuality-detection-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse