drwlf/Medra4b-abliterated
Full fine-tune vs google/gemma-3-4b-it. Fine-tune: 90% of the weights changed, across 34 of 34 layers.
Tensors changed: Embeddings 1/4, Norms 0/316, MLP 102/210, Attention 136/352, other 0/1
3 derivatives checked
- Guilherme34/Medra4b-abliterated-i1-VISION-GGUF: Quantization (fewer layers)
- mradermacher/Medra4b-abliterated-i1-GGUF: Quantization (fewer layers)
- mradermacher/Medra4b-abliterated-GGUF: Same weights, converted (fewer layers)
1 other repos hold byte-for-byte identical weight files.