fterry/FoFoNet-SuperMBX-slerp

Full fine-tune vs flemmingmiguel/MBX-7B-v3. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 24/65, MLP 93/96, Attention 124/128, lm_head 1/1

3 derivatives checked

• mradermacher/FoFoNet-SuperMBX-slerp-i1-GGUF: Quantization
• mradermacher/FoFoNet-SuperMBX-slerp-GGUF: Same weights, converted
• fterry/FoFoNet-SuperMayo-MBX-slerp: Full fine-tune

On the Hub · Downloads on Model Pulse