ichigoberry/pandafish-2-7b-32k

Full fine-tune vs dphn/dolphin-2.8-mistral-7b-v02. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 15/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/pandafish-2-7b-32k-GGUF: Quantization
• featherless-ai-quants/ichigoberry-pandafish-2-7b-32k-GGUF: Quantization

On the Hub · Downloads on Model Pulse