arcee-ai/Arcee-Maestro-7B-Preview
Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Attention 194/196, MLP 84/84, Norms 37/57
7 derivatives checked
- bartowski/arcee-ai_Arcee-Maestro-7B-Preview-GGUF: Quantization
- arcee-ai/Arcee-Maestro-7B-Preview-GGUF: Quantization
- brittlewis12/Arcee-Maestro-7B-Preview-GGUF: Same weights, converted
- DevQuasar-8/arcee-ai.Arcee-Maestro-7B-Preview-GGUF: Same weights, converted
- mradermacher/Arcee-Maestro-7B-Preview-GGUF: Same weights, converted
- bunnycore/Maestro-S1k-7B-Sce: Full fine-tune
- bunnycore/S1K-Maestro-7B-Sce: Full fine-tune
1 other repos hold byte-for-byte identical weight files.