anthracite-org/magnum-v2-72b
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 125/161, lm_head 1/1
3 derivatives checked
- anthracite-org/magnum-v2-72b-gguf: Same weights, converted
- mradermacher/magnum-v2-72b-i1-GGUF: Quantization
- mradermacher/magnum-v2-72b-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.