prithivMLmods/Lambda-Equulei-1.5B-xLingual
Full fine-tune vs Qwen/Qwen2.5-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196
3 derivatives checked
- prithivMLmods/Lambda-Equulei-1.5B-xLingual-GGUF: Same weights, converted
- mradermacher/Lambda-Equulei-1.5B-xLingual-GGUF: Same weights, converted
- mradermacher/Lambda-Equulei-1.5B-xLingual-i1-GGUF: Quantization