rodrigomt/quem-V2-4b

Full fine-tune vs GetSoloTech/Qwen3-Code-Reasoning-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 111/145, MLP 108/108, Attention 144/144

1 derivatives checked

• rodrigomt/quem-V2-4b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse