SEACrowd/Gemma-SEA-LION-v4-27B-VL
Full fine-tune vs aisingapore/Gemma-SEA-LION-v4-27B-IT. Fine-tune: 100% of the weights changed, across 62 of 62 layers.
Tensors changed: Embeddings 4/4, Norms 484/484, MLP 294/294, Attention 464/464, other 1/1
2 derivatives checked
- mradermacher/Gemma-SEA-LION-v4-27B-VL-i1-GGUF: Quantization (fewer layers)
- mradermacher/Gemma-SEA-LION-v4-27B-VL-GGUF: Quantization (fewer layers)
1 other repos hold byte-for-byte identical weight files.