bunnycore/FuseQwQen-7B
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
6 derivatives checked
- mradermacher/FuseQwQen-7B-GGUF: Same weights, converted
- mradermacher/FuseQwQen-7B-i1-GGUF: Quantization
- MaziyarPanahi/FuseQwQen-7B-GGUF: Same weights, converted
- bunnycore/FwF-Qwen-7B-0.2: Full fine-tune
- bunnycore/FwF-Qwen-7B-0.1: Full fine-tune
- bunnycore/Qwen-7B-MixLow: Full fine-tune