Yuma42/Llama3.1-LoyalLizard-8B

Partial fine-tune vs Yuma42/Llama3.1-IgneousIguana-8B. Partial change: 87% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Llama3.1-LoyalLizard-8B-GGUF: Same weights, converted
• Yuma42/Llama3.1-DeepDilemma-V0.9-8B: Partial fine-tune

On the Hub · Downloads on Model Pulse