sandmanbuzz/MistralThinker-v1.1-Reasoner-256

Full fine-tune vs Undi95/MistralThinker-v1.1. Fine-tune: 94% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 11/81, MLP 120/120, Attention 160/160, lm_head 0/1

2 derivatives checked

On the Hub · Downloads on Model Pulse