Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP

Partial fine-tune vs google/gemma-4-E4B-it. Partial change: 55% of the weights changed (attention, mlp, other), in 42 of 42 layers.

Tensors changed: MLP 222/606, Norms 0/502, other 24/261, Attention 263/755, Embeddings 0/6

3 derivatives checked

• mradermacher/gemma-4-E4B-it-SDFT_Heretic_RP-i1-GGUF: Quantization (fewer layers)
• Ilya626/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF: Quantization (fewer layers)
• mradermacher/gemma-4-E4B-it-SDFT_Heretic_RP-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse