nbeerbower/EVA-abliterated-TIES-Qwen2.5-1.5B
Full fine-tune vs EVA-UNIT-01/EVA-Qwen2.5-1.5B-v0.0. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 55/57, MLP 84/84, Attention 196/196
4 derivatives checked
- mradermacher/EVA-abliterated-TIES-Qwen2.5-1.5B-i1-GGUF: Quantization
- mradermacher/EVA-abliterated-TIES-Qwen2.5-1.5B-GGUF: Same weights, converted
- nbeerbower/Dumpling-Qwen2.5-1.5B: LoRA-style
- nbeerbower/Dumpling-Qwen2.5-1.5B-v2: LoRA-style