grimjim/llama-3-Nephilim-v3-8B
Full fine-tune vs grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 58/65, MLP 96/96, Attention 128/128
7 derivatives checked
- bartowski/llama-3-Nephilim-v3-8B-GGUF: Quantization
- mradermacher/llama-3-Nephilim-v3-8B-i1-GGUF: Quantization
- mradermacher/llama-3-Nephilim-v3-8B-GGUF: Same weights, converted
- featherless-ai-quants/grimjim-llama-3-Nephilim-v3-8B-GGUF: Quantization
- grimjim/llama-3-Nephilim-v3-8B-GGUF: Quantization
- grimjim/Llama-Nephilim-Metamorphosis-v2-8B: Full fine-tune
- grimjim/Llama-Nephilim-Metamorphosis-v1-8B: Full fine-tune