ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes
Full fine-tune vs ZeroXClem/L3SAO-Mix-SuperHermes-NovaPurosani-8B. 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
5 derivatives checked
- mradermacher/Llama-3.1-8B-SuperNova-EtherealHermes-i1-GGUF: Quantization
- mradermacher/Llama-3.1-8B-SuperNova-EtherealHermes-GGUF: Same weights, converted
- MaziyarPanahi/Llama-3.1-8B-SuperNova-EtherealHermes-GGUF: Same weights, converted
- tensorblock/Llama-3.1-8B-SuperNova-EtherealHermes-GGUF: Quantization
- ZeroXClem/Llama-3.1-8B-RainbowLight-EtherealMix: Full fine-tune