CultriX/Qwen2.5-14B-Unity
Full fine-tune vs CultriX/Qwen2.5-14B-Wernickev3. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336
3 derivatives checked
- mradermacher/Qwen2.5-14B-Unity-i1-GGUF: Quantization
- mradermacher/Qwen2.5-14B-Unity-GGUF: Quantization
- MaziyarPanahi/Qwen2.5-14B-Unity-GGUF: Same weights, converted