ZeroXClem/Qwen2.5-7B-CelestialHarmony-1M
Partial fine-tune vs Qwen/Qwen2.5-7B-Instruct-1M. Partial change: 54% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Norms 1/57, MLP 42/84, Attention 81/196
3 derivatives checked
- mradermacher/Qwen2.5-7B-CelestialHarmony-1M-i1-GGUF: Quantization
- mradermacher/Qwen2.5-7B-CelestialHarmony-1M-GGUF: Same weights, converted
- DevQuasar-9/ZeroXClem.Qwen2.5-7B-CelestialHarmony-1M-GGUF: Same weights, converted