YOYO-AI/ZYH-LLM-Qwen2.5-14B-V3
Full fine-tune vs Azure99/Blossom-V6-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: MLP 144/144, Attention 336/336, Norms 97/97
3 derivatives checked
- mradermacher/ZYH-LLM-Qwen2.5-14B-V3-i1-GGUF: Quantization
- mradermacher/ZYH-LLM-Qwen2.5-14B-V3-GGUF: Quantization
- MaziyarPanahi/ZYH-LLM-Qwen2.5-14B-V3-GGUF: Same weights, converted