djuna/Q2.5-Veltha-14B-0.5
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: Norms 97/97, MLP 144/144, Attention 336/336
4 derivatives checked
- bartowski/Q2.5-Veltha-14B-0.5-GGUF: Same weights, converted
- mradermacher/Q2.5-Veltha-14B-0.5-i1-GGUF: Quantization
- mradermacher/Q2.5-Veltha-14B-0.5-GGUF: Quantization
- djuna/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-remap: Full fine-tune