muzerai/Llama-3.1-KoEn-8B-magic8

Full fine-tune vs akjindal53244/Llama-3.1-Storm-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 11/65, MLP 96/96, Attention 128/128

1 derivatives checked

• mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse