djuna/Q2.5-Veltha-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: Norms 97/97, MLP 144/144, Attention 336/336
5 derivatives checked
- mradermacher/Q2.5-Veltha-14B-i1-GGUF: Quantization
- mradermacher/Q2.5-Veltha-14B-GGUF: Quantization
- attashe/q-2.5-deepseek-r1-veltha-v0.3: Full fine-tune
- Sakalti/SJT-14B: Partial fine-tune
- bamec66557/Qwen-2.5-14B-MINUS: Partial fine-tune