grimjim/Llama-3-Luminurse-v0.2-OAS-8B
Full fine-tune vs NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 26/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/Llama-3-Luminurse-v0.2-OAS-8B-GGUF: Same weights, converted
- mradermacher/Llama-3-Luminurse-v0.2-OAS-8B-i1-GGUF: Quantization
- featherless-ai-quants/grimjim-Llama-3-Luminurse-v0.2-OAS-8B-GGUF: Quantization