vazirani/ThoughtWeaver-8B-Reasoning-Exp

Full fine-tune vs unsloth/Ministral-3-8B-Instruct-2512. Fine-tune: 95% of the weights changed, across 34 of 34 layers.

Tensors changed: Embeddings 1/1, Norms 0/119, MLP 102/174, Attention 136/232, other 0/4, lm_head 1/1

1 derivatives checked

• vazirani/ThoughtWeaver-8B-Reasoning-Exp-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse