dphn/Dolphin3.0-Qwen2.5-0.5B
Full fine-tune vs Qwen/Qwen2.5-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 168/168
6 derivatives checked
- bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF: Same weights, converted
- DevQuasar-7/cognitivecomputations.Dolphin3.0-Qwen2.5-0.5B-GGUF: Same weights, converted
- mradermacher/Dolphin3.0-Qwen2.5-0.5B-i1-GGUF: Quantization
- mradermacher/Dolphin3.0-Qwen2.5-0.5B-GGUF: Same weights, converted
- itlwas/Dolphin3.0-Qwen2.5-0.5B-Q4_K_M-GGUF: Quantization
- Emilio407/Dolphin3.0-Qwen2.5-0.5B-GRPO-V1: LoRA-style
1 other repos hold byte-for-byte identical weight files.