noirchan/Llama-3-8B_Suzume_DARE_TIES0.5_v2

Full fine-tune vs lightblue/suzume-llama-3-8B-japanese. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 15/65, MLP 96/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• mradermacher/Llama-3-8B_Suzume_DARE_TIES0.5_v2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse