pszemraj/granite-4.0-h-1b-heretic

Full fine-tune vs ibm-granite/granite-4.0-h-1b-base. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 117/117, other 252/252, MLP 80/80, Attention 16/16

2 derivatives checked

• mradermacher/granite-4.0-h-1b-heretic-i1-GGUF: Quantization
• mradermacher/granite-4.0-h-1b-heretic-GGUF: Abliterated

On the Hub · Downloads on Model Pulse