Praneeth/StarMix-7B-slerp

Full fine-tune vs berkeley-nest/Starling-LM-7B-alpha. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 93/96, Attention 124/128

2 derivatives checked

• mradermacher/StarMix-7B-slerp-i1-GGUF: Quantization
• mradermacher/StarMix-7B-slerp-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse