Yuma42/Llama3.1-SuperHawk-8B
Full fine-tune vs Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base. 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
4 derivatives checked
- mradermacher/Llama3.1-SuperHawk-8B-i1-GGUF: Quantization
- mradermacher/Llama3.1-SuperHawk-8B-GGUF: Same weights, converted
- Yuma42/Llama3.1-IgneousIguana-8B: Full fine-tune
- ChiKoi7/Llama3.1-IgneousIguana-8B-Heretic: Full fine-tune