EVA-UNIT-01/EVA-Qwen2.5-1.5B-v0.0
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
- mradermacher/EVA-Qwen2.5-1.5B-v0.0-GGUF: Same weights, converted
- DevQuasar-9/EVA-UNIT-01.EVA-Qwen2.5-1.5B-v0.0-GGUF: Same weights, converted
- nbeerbower/EVA-abliterated-TIES-Qwen2.5-1.5B: Full fine-tune