mistralai/Magistral-Small-2507
Full fine-tune (fewer layers) vs mistralai/Mistral-Small-3.1-24B-Instruct-2503. mistralai/Magistral-Small-2507 matches part of mistralai/Mistral-Small-3.1-24B-Instruct-2503 (363 of its 585 tensors; the rest of mistralai/Mistral-Small-3.1-24B-Instruct-2503 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 40/81, MLP 120/120, Attention 160/160, lm_head 1/1
7 derivatives checked
- bartowski/mistralai_Magistral-Small-2507-GGUF: Same weights, converted
- unsloth/Magistral-Small-2507-GGUF: Same weights, converted
- gabriellarson/Magistral-Small-2507-GGUF: Quantization
- mistralai/Magistral-Small-2507-GGUF: Same weights, converted
- lmstudio-community/Magistral-Small-2507-GGUF: Quantization
- Silicone-Moss/MistralAI-Magistral-Small-2507-Heretic-Uncensored: Abliterated
- kmouratidis/Magistral-Small-2507-Rebased-Vision: Same weights, converted (fewer layers)