MultiverseComputingCAI/Hypernova-60B-2605

Full fine-tune vs MultiverseComputingCAI/HyperNova-60B. Fine-tune: 96% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 245/256, Attention 128/288, lm_head 1/1

2 derivatives checked

• mradermacher/Hypernova-60B-2605-i1-GGUF: Quantization
• mradermacher/Hypernova-60B-2605-GGUF: Quantization

On the Hub · Downloads on Model Pulse