grimjim/Mistral-Starling-merge-trial1-7B

Full fine-tune vs Nexusflow/Starling-LM-7B-beta. 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/Mistral-Starling-merge-trial1-7B-i1-GGUF: Quantization
• grimjim/cuckoo-starling-32k-7B: Full fine-tune

On the Hub · Downloads on Model Pulse