Alfitaria/Q25-1.5B-VeoLu
Partial fine-tune vs Qwen/Qwen2.5-1.5B-Instruct. Partial change: 85% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 1/57, MLP 84/84, Attention 113/196
5 derivatives checked
- bartowski/Q25-1.5B-VeoLu-GGUF: Same weights, converted
- mradermacher/Q25-1.5B-VeoLu-i1-GGUF: Quantization
- mradermacher/Q25-1.5B-VeoLu-GGUF: Same weights, converted
- DevQuasar-6/Alfitaria.Q25-1.5B-VeoLu-GGUF: Quantization
- mergekit-community/DeepVeo-R1-B: Full fine-tune