Qiskit/granite-3.3-8b-qiskit

Full fine-tune vs ibm-granite/granite-3.3-8b-instruct. Fine-tune: 98% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 81/81, MLP 117/120, Attention 152/160

3 derivatives checked

• mradermacher/granite-3.3-8b-qiskit-i1-GGUF: Quantization
• mradermacher/granite-3.3-8b-qiskit-GGUF: Same weights, converted
• DevQuasar/Qiskit.granite-3.3-8b-qiskit-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse