YOYO-AI/ZYH-LLM-Qwen2.5-14B-V2
Full fine-tune vs Qwen/Qwen2.5-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 97/97, MLP 144/144, Attention 336/336
3 derivatives checked
- mradermacher/ZYH-LLM-Qwen2.5-14B-V2-i1-GGUF: Quantization
- YOYO-AI/ZYH-LLM-Qwen2.5-14B-V2-GGUF: Same weights, converted
- mradermacher/ZYH-LLM-Qwen2.5-14B-V2-GGUF: Quantization