aisingapore/Apertus-SEA-LION-v4-8B-IT
Full fine-tune vs swiss-ai/Apertus-8B-Instruct-2509. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 45/129, MLP 64/192, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/Apertus-SEA-LION-v4-8B-IT-i1-GGUF: Quantization
- mradermacher/Apertus-SEA-LION-v4-8B-IT-GGUF: Same weights, converted
- mlx-community/Apertus-SEA-LION-v4-8B-IT: Same weights, repacked