dphn/dolphin-2.9.2-qwen2-72b
Partial fine-tune vs Qwen/Qwen2-72B. Partial change: 47% of the weights changed (attention, embeddings, lm_head, mlp), in 79 of 80 layers.
Tensors changed: Embeddings 1/1, MLP 108/240, Attention 252/560, Norms 0/161, lm_head 1/1
3 derivatives checked
- mradermacher/dolphin-2.9.2-qwen2-72b-i1-GGUF: Quantization
- mradermacher/dolphin-2.9.2-qwen2-72b-GGUF: Quantization
- featherless-ai-quants/cognitivecomputations-dolphin-2.9.2-qwen2-72b-GGUF: Quantization
4 other repos hold byte-for-byte identical weight files.