mayacinka/Open-StaMis-v02-stock

Full fine-tune vs Nexusflow/Starling-LM-7B-beta. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128

1 derivatives checked

• featherless-ai-quants/mayacinka-Open-StaMis-v02-stock-GGUF: Quantization

On the Hub · Downloads on Model Pulse