swiss-ai/Apertus-v1.1-1.5B-Instruct
Full fine-tune vs swiss-ai/Apertus-v1.1-1.5B. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 64/65, MLP 55/96, Attention 64/64
4 derivatives checked
- mradermacher/Apertus-v1.1-1.5B-Instruct-GGUF: Same weights, converted
- DMP96/Apertus-v1.1-1.5B-Instruct-QAD-Q4_1-GGUF: Full fine-tune
- vpakarinen/Lumo-1-1.5B-Chat: Partial fine-tune
- vpakarinen/Lumo-1-1.5B-Chat-V2: Partial fine-tune