shisa-ai/shisa-v2-llama3.1-405b

Full fine-tune vs meta-llama/Llama-3.1-405B-Instruct. Fine-tune: 99% of the weights changed, across 126 of 126 layers.

Tensors changed: Embeddings 0/1, Attention 504/504, MLP 378/378, Norms 250/253, lm_head 1/1

2 derivatives checked

• shisa-ai/shisa-v2-llama3.1-405b-GGUF: Quantization
• DevQuasar/shisa-ai.shisa-v2-llama3.1-405b-GGUF: Quantization

On the Hub · Downloads on Model Pulse