MirilAI/Miril-Drone-2B-1

Partial fine-tune vs google/gemma-4-E2B-it. Partial change: 11% of the weights changed (attention, embeddings), in 35 of 35 layers.

Tensors changed: MLP 0/585, Norms 0/433, other 0/240, Attention 50/687, Embeddings 1/6

2 derivatives checked

• bartowski/MirilAI_Miril-Drone-2B-1-GGUF: Same weights, converted (fewer layers)
• mradermacher/Miril-Drone-2B-1-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse