Yuma42/Llama3.1-IgneousIguana-8B

Full fine-tune vs Yuma42/Llama3.1-SuperHawk-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

3 derivatives checked

• mradermacher/Llama3.1-IgneousIguana-8B-i1-GGUF: Quantization
• mradermacher/Llama3.1-IgneousIguana-8B-GGUF: Same weights, converted
• Yuma42/Llama3.1-LoyalLizard-8B: Partial fine-tune

On the Hub · Downloads on Model Pulse