ChaoticNeutrals/Poppy_Porpoise-v0.4-L3-8B
Full fine-tune vs dphn/dolphin-2.9-llama3-8b. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 93/96, Attention 124/128
3 derivatives checked
- featherless-ai-quants/ChaoticNeutrals-Poppy_Porpoise-v0.4-L3-8B-GGUF: Quantization
- mradermacher/Poppy_Porpoise-v0.4-L3-8B-i1-GGUF: Quantization
- mradermacher/Poppy_Porpoise-v0.4-L3-8B-GGUF: Same weights, converted