inclusionAI/Ring-mini-2.0
Full fine-tune vs inclusionAI/Ling-mini-base-2.0-20T. Fine-tune: 100% of the weights changed, across 20 of 20 layers.
Tensors changed: MLP 2725/2729, Embeddings 1/1, lm_head 1/1, Attention 40/40, Norms 81/81
8 derivatives checked
- inclusionAI/Ring-mini-2.0-GGUF: Same weights, converted
- bartowski/inclusionAI_Ring-mini-2.0-GGUF: Same weights, converted
- mradermacher/Ring-mini-2.0-i1-GGUF: Quantization
- mradermacher/Ring-mini-2.0-GGUF: Quantization
- redponike/Ring-mini-2.0-GGUF: Quantization
- redponike/Ring-mini-2.0-GGUF-ik: Quantization
- DevQuasar/inclusionAI.Ring-mini-2.0-GGUF: Same weights, converted
- qingy2024/Pristine-Mini-8B-A1B-Base: LoRA-style (fewer layers)
1 other repos hold byte-for-byte identical weight files.