noeme/Lura-1.3-500m
Full fine-tune vs Qwen/Qwen2.5-0.5B-Instruct. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 38/49, MLP 72/72, Attention 168/168
1 derivatives checked
- mradermacher/Lura-1.3-500m-GGUF: Same weights, converted