Xiaojian9992024/Reflection-L3.2-JametMiniMix-3B

Full fine-tune vs Hastagaras/L3.2-JametMini-3B-MK.III. Fine-tune: 97% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 15/57, MLP 81/84, Attention 108/112

1 derivatives checked

• mradermacher/Reflection-L3.2-JametMiniMix-3B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse