vpakarinen/Lumo-1-1.5B-Chat-V2
Partial fine-tune vs swiss-ai/Apertus-v1.1-1.5B-Instruct. Partial change: 82% of the weights changed (attention, lm_head, mlp, norms), in 16 of 16 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 8/65, MLP 32/96, Attention 64/64
2 derivatives checked
- mradermacher/Lumo-1-1.5B-Chat-V2-i1-GGUF: Quantization
- mradermacher/Lumo-1-1.5B-Chat-V2-GGUF: Same weights, converted