nbeerbower/EVA-abliterated-Qwen2.5-7B
Full fine-tune vs EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1. 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, lm_head 1/1
8 derivatives checked
- mradermacher/EVA-abliterated-Qwen2.5-7B-i1-GGUF: Quantization
- PrunaAI/nbeerbower-EVA-abliterated-Qwen2.5-7B-GGUF-smashed: Quantization
- mradermacher/EVA-abliterated-Qwen2.5-7B-GGUF: Same weights, converted
- nbeerbower/Dumpling-Qwen2.5-7B-1k-r64-2e-5: LoRA-style
- nbeerbower/Dumpling-Qwen2.5-7B-1k-r16: LoRA-style
- nbeerbower/Dumpling-Qwen2.5-7B-1k-r32: LoRA-style
- nbeerbower/Dumpling-Qwen2.5-7B-1k-r32-2e-5: LoRA-style
- nbeerbower/Dumpling-Qwen2.5-7B-1k-r256: LoRA-style