juiceb0xc0de/bella-bartender-gemma-e2b

Partial fine-tune vs google/gemma-4-E2B-it. Partial change: 37% of the weights changed (attention, mlp, norms, other), in 35 of 35 layers.

Tensors changed: MLP 105/585, Norms 119/433, other 71/240, Attention 100/687, Embeddings 0/6

3 derivatives checked

• mradermacher/bella-bartender-gemma-e2b-i1-GGUF: Quantization (fewer layers)
• mradermacher/bella-bartender-gemma-e2b-GGUF: Same weights, converted (fewer layers)
• juiceb0xc0de/bella-bartender-gemma-4-e2b-gguf: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse