SteelStorage/L3-Aethora-15B-V2
Partial fine-tune vs elinas/Llama-3-15B-Instruct-zeroed. Partial change: 89% of the weights changed (attention, lm_head, mlp), in 64 of 64 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 0/129, MLP 178/192, Attention 222/256
5 derivatives checked
- mradermacher/L3-Aethora-15B-V2-i1-GGUF: Quantization
- mradermacher/L3-Aethora-15B-V2-GGUF: Quantization
- QuantFactory/L3-Aethora-15B-V2-GGUF: Quantization
- featherless-ai-quants/ZeusLabs-L3-Aethora-15B-V2-GGUF: Quantization
- kromeurus/L3-Blackfall-Summanus-v0.1-15B: Full fine-tune