aion-labs/Aion-RP-Llama-3.1-8B
Full fine-tune vs meta-llama/Llama-3.1-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 62/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- bartowski/Aion-RP-Llama-3.1-8B-GGUF: Same weights, converted
- mradermacher/Aion-RP-Llama-3.1-8B-i1-GGUF: Quantization
- mradermacher/Aion-RP-Llama-3.1-8B-GGUF: Same weights, converted