anthracite-org/magnum-v2-32b
Full fine-tune vs Qwen/Qwen1.5-32B. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 125/129, MLP 192/192, Attention 448/448, lm_head 1/1
7 derivatives checked
- anthracite-org/magnum-v2-32b-gguf: Quantization
- bartowski/magnum-32b-v2-GGUF: Quantization
- mradermacher/magnum-v2-32b-GGUF: Quantization
- mradermacher/magnum-32b-v2-i1-GGUF: Quantization
- mradermacher/magnum-32b-v2-GGUF: Quantization
- mradermacher/magnum-v2-32b-i1-GGUF: Quantization
- SmileyTatsu/magnum-32b-v2-Q4_K_M-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.