Neura-Tech-AI/Neuron-46x4B
Same weights, repacked vs Neura-Tech-AI/Neuron-4B-Instruct. Same weights in different files (re-saved, re-sharded or new metadata), plus 108 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/145, Attention 0/144
4 derivatives checked
- mradermacher/Neuron-46x4B-Instruct-i1-GGUF: Quantization
- mradermacher/Neuron-46x4B-i1-GGUF: Quantization
- mradermacher/Neuron-46x4B-GGUF: Quantization
- mradermacher/Neuron-46x4B-Instruct-GGUF: Quantization