nbeerbower/EVA-abliterated-TIES-Qwen2.5-72B
Full fine-tune vs EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 147/161, MLP 240/240, Attention 560/560, lm_head 1/1
3 derivatives checked
- mradermacher/EVA-abliterated-TIES-Qwen2.5-72B-i1-GGUF: Quantization
- mradermacher/EVA-abliterated-TIES-Qwen2.5-72B-GGUF: Quantization
- nbeerbower/Dumpling-Qwen2.5-72B: LoRA-style