rhplus0831/maid-yuzu-v2-alter

Full fine-tune vs smelborp/MixtralOrochi8x7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, MLP 768/768, other 32/32, Norms 65/65, Attention 128/128, lm_head 1/1

1 derivatives checked

• mradermacher/maid-yuzu-v2-alter-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse