Shidokaizaki/Dolphin-Mistral-24B-Venice-Edition
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-24B-Instruct-2501. mistralai/Mistral-Small-24B-Instruct-2501 matches part of Shidokaizaki/Dolphin-Mistral-24B-Venice-Edition (363 of its 585 tensors; the rest of Shidokaizaki/Dolphin-Mistral-24B-Venice-Edition has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 81/81, MLP 120/120, Attention 160/160, lm_head 1/1
18 other repos hold byte-for-byte identical weight files.