anthracite-org/magnum-v1-72b
Full fine-tune vs Qwen/Qwen2-72B-Instruct. Fine-tune: 98% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, MLP 240/240, Attention 560/560, Norms 129/161, lm_head 1/1
7 derivatives checked
- bartowski/magnum-72b-v1-GGUF: Same weights, converted
- mradermacher/magnum-72b-v1-i1-GGUF: Quantization
- backyardai/magnum-72b-v1-GGUF: Quantization
- mradermacher/magnum-72b-v1-GGUF: Quantization
- featherless-ai-quants/alpindale-magnum-72b-v1-GGUF: Quantization
- featherless-ai-quants/anthracite-org-magnum-v1-72b-GGUF: Quantization
- smelborp/StellarDong-72b: Full fine-tune