PhilflowIO/gemma-3-12b-it-antislop-de

Partial fine-tune vs google/gemma-3-12b-it. Partial change: 55% of the weights changed (embeddings, mlp), in 48 of 48 layers.

Tensors changed: Embeddings 1/4, Norms 0/400, MLP 96/252, Attention 0/408, other 0/1

2 derivatives checked

• mradermacher/gemma-3-12b-it-antislop-de-i1-GGUF: Quantization (fewer layers)
• mradermacher/gemma-3-12b-it-antislop-de-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse