dphn/dolphin-2.9.2-qwen2-7b
Full fine-tune vs Qwen/Qwen2-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1
6 derivatives checked
- QuantFactory/dolphin-2.9.2-qwen2-7b-GGUF: Quantization
- mradermacher/dolphin-2.9.2-qwen2-7b-i1-GGUF: Quantization
- mradermacher/dolphin-2.9.2-qwen2-7b-GGUF: Same weights, converted
- waltervix/dolphin-2.9.2-qwen2-7b-Q4_K_M-GGUF: Quantization
- tensorblock/dolphin-2.9.2-qwen2-7b-GGUF: Quantization
- itlwas/dolphin-2.9.2-qwen2-7b-Q4_K_M-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.