BricksDisplay/jevling-e2b-v1

Partial fine-tune vs google/gemma-4-E2B-it. Partial change: 36% of the weights changed (attention, mlp, norms), in 35 of 35 layers.

Tensors changed: MLP 105/585, Norms 1/433, other 0/240, Attention 100/687, Embeddings 0/6

1 derivatives checked

• BricksDisplay/jevling-e2b-v1-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse