mradermacher/ablation-187-gemma3.webnovels.test.gemma-3-4b-GGUF

Same weights, converted vs shisa-ai/ablation-187-gemma3.webnovels.test.gemma-3-4b. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136

On the Hub · Downloads on Model Pulse