bunnycore/Llama-3.1-8B-TitanFusion-Mix
Full fine-tune vs bunnycore/Llama-3.1-8B-TitanFusion. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
4 derivatives checked
- mradermacher/Llama-3.1-8B-TitanFusion-Mix-i1-GGUF: Quantization
- mradermacher/Llama-3.1-8B-TitanFusion-Mix-GGUF: Same weights, converted
- ZeroXClem/Llama-3.1-8B-SpecialTitanFusion: Full fine-tune
- jaspionjader/Kosmos-EVAA-v9-TitanFusion-Mix-8B: Full fine-tune