ibm-granite/granite-3.2-8b-instruct-preview
Full fine-tune vs ibm-granite/granite-3.1-8b-instruct. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 70/81, MLP 120/120, Attention 148/160
4 derivatives checked
- mradermacher/granite-3.2-8b-instruct-preview-i1-GGUF: Quantization
- DevQuasar-7/ibm-granite.granite-3.2-8b-instruct-preview-GGUF: Same weights, converted
- mradermacher/granite-3.2-8b-instruct-preview-GGUF: Same weights, converted
- cgus/granite-3.2-8b-instruct-preview-iMat-GGUF: Quantization