bunnycore/FuseCyberMix-Qwen-2.5-7B-Instruct
Full fine-tune vs FuseAI/FuseChat-Qwen-2.5-7B-Instruct. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1
3 derivatives checked
- mradermacher/FuseCyberMix-Qwen-2.5-7B-Instruct-i1-GGUF: Quantization
- mradermacher/FuseCyberMix-Qwen-2.5-7B-Instruct-GGUF: Same weights, converted
- MaziyarPanahi/FuseCyberMix-Qwen-2.5-7B-Instruct-GGUF: Same weights, converted