sometimesanotion/Qwen2.5-14B-Vimarckoso-v3
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
- mradermacher/Qwen2.5-14B-Vimarckoso-v3-GGUF: Quantization
- mradermacher/Qwen2.5-14B-Vimarckoso-v3-i1-GGUF: Quantization
- MaziyarPanahi/Qwen2.5-14B-Vimarckoso-v3-GGUF: Same weights, converted
- Sakalti/ultiima-14B-v0.3: Partial fine-tune