mergekit-community/24B-MS-PRO-V0.01
Full fine-tune vs dphn/Dolphin3.0-Mistral-24B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 3/81, MLP 120/120, Attention 160/160, lm_head 1/1
1 derivatives checked
- mradermacher/24B-MS-PRO-V0.01-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.