Casual-Autopsy/L3-Luna-8B
Full fine-tune vs Ayush-1722/Meta-Llama-3-8B-Instruct-Summarize-v0.2-24K-LoRANET-Merged. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
3 derivatives checked
- bartowski/L3-Luna-8B-GGUF: Same weights, converted
- mradermacher/L3-Luna-8B-i1-GGUF: Quantization
- mradermacher/L3-Luna-8B-GGUF: Same weights, converted