MaziyarPanahi/calme-2.3-qwen2-7b
Partial fine-tune vs Qwen/Qwen2-7B. Partial change: 85% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 55/57, MLP 83/84, Attention 196/196, lm_head 0/1
4 derivatives checked
- mradermacher/calme-2.3-qwen2-7b-i1-GGUF: Quantization
- mradermacher/calme-2.3-qwen2-7b-GGUF: Same weights, converted
- MaziyarPanahi/calme-2.3-qwen2-7b-GGUF: Same weights, converted
- featherless-ai-quants/MaziyarPanahi-calme-2.3-qwen2-7b-GGUF: Quantization