nbeerbower/EVA-abliterated-TIES-Qwen2.5-14B
Full fine-tune vs EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336, lm_head 1/1
4 derivatives checked
- KiyoEditz/EVA-abliterated-TIES-Qwen2.5-14B-i1-GGUF: Quantization
- mradermacher/EVA-abliterated-TIES-Qwen2.5-14B-i1-GGUF: Quantization
- mradermacher/EVA-abliterated-TIES-Qwen2.5-14B-GGUF: Quantization
- nbeerbower/Dumpling-Qwen2.5-14B: LoRA-style
1 other repos hold byte-for-byte identical weight files.