Neura-Tech-AI/Neuron-V1-14B-Instruct
Same weights, converted vs Qwen/Qwen2.5-14B-Instruct. Same weights stored in another dtype (BF16 → F16).
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/336, lm_head 0/1
6 derivatives checked
- mradermacher/Neuron-V1-Distill-Qwen2-14B-i1-GGUF: Quantization
- mradermacher/Neuron-V1-14B-Instruct-i1-GGUF: Quantization
- mradermacher/Neuron-14B-i1-GGUF: Quantization
- mradermacher/Neuron-V1-Distill-Qwen2-14B-GGUF: Quantization
- mradermacher/Neuron-V1-14B-Instruct-GGUF: Quantization
- mradermacher/Neuron-14B-GGUF: Quantization