NovaCorp/CULO-MoE
Full fine-tune vs MOHAMEDSANAF2001/llama3.2-1b-merged-2. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 33/33, MLP 48/48, Attention 64/64
5 derivatives checked
- mradermacher/CULO-MoE-i1-GGUF: Quantization
- mradermacher/Llama3.2-CULO-1B-i1-GGUF: Quantization
- mradermacher/Llama3.2-CULO-1B-GGUF: Same weights, converted
- Novaciano/Llama3.2-CULO-1B-GGUF: Same weights, converted
- mradermacher/CULO-MoE-GGUF: Same weights, converted