MaziyarPanahi/calme-2.4-qwen2-7b
Full fine-tune vs Qwen/Qwen2-7B. Fine-tune: 92% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 54/57, MLP 83/84, Attention 196/196, lm_head 1/1
4 derivatives checked
- mradermacher/calme-2.4-qwen2-7b-i1-GGUF: Quantization
- mradermacher/calme-2.4-qwen2-7b-GGUF: Same weights, converted
- MaziyarPanahi/calme-2.4-qwen2-7b-GGUF: Same weights, converted
- tensorblock/calme-2.4-qwen2-7b-GGUF: Quantization