artificialguybr/QWEN-2-1.5B-Synthia-I
Full fine-tune vs Qwen/Qwen2-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 57/57, MLP 84/84, Attention 192/196
3 derivatives checked
- artificialguybr/QWEN-2-1.5B-Synthia-I-gguf: Same weights, converted
- mradermacher/QWEN-2-1.5B-Synthia-I-i1-GGUF: Quantization
- mradermacher/QWEN-2-1.5B-Synthia-I-GGUF: Same weights, converted