MaziyarPanahi/calme-2.2-qwen2-72b
Full fine-tune vs Qwen/Qwen2-72B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, MLP 240/240, Attention 560/560, Norms 161/161, lm_head 1/1
4 derivatives checked
- bartowski/calme-2.2-qwen2-72b-GGUF: Quantization
- mradermacher/calme-2.2-qwen2-72b-GGUF: Quantization
- mradermacher/calme-2.2-qwen2-72b-i1-GGUF: Quantization
- featherless-ai-quants/MaziyarPanahi-calme-2.2-qwen2-72b-GGUF: Quantization