Naphula-Archives/MistralThinker-AntiRep-24B-v1

Full fine-tune vs ConicCat/Mistral-Small-3.2-AntiRep-24B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 4/81, MLP 120/120, Attention 160/160, lm_head 1/1

2 derivatives checked

On the Hub · Downloads on Model Pulse