OEvortex/HelpingAI-Lite-2x1B
MoE built from dense models vs OEvortex/HelpingAI-Lite. OEvortex/HelpingAI-Lite-2x1B is a mixture of 2 experts assembled from dense models (mergekit-moe style): experts 0, 1 are an exact copy of OEvortex/HelpingAI-Lite's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 135 of 135 identical.
3 derivatives checked
- mradermacher/HelpingAI-Lite-2x1B-i1-GGUF: Quantization
- mradermacher/HelpingAI-Lite-2x1B-GGUF: Same weights, converted
- tensorblock/HelpingAI-Lite-2x1B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.