inclusionAI/Ling-mini-2.0
Full fine-tune vs inclusionAI/Ling-mini-base-2.0. Fine-tune: 100% of the weights changed, across 20 of 20 layers.
Tensors changed: Attention 40/40, Norms 81/81, MLP 2725/2729, Embeddings 1/1, lm_head 1/1
9 derivatives checked
- inclusionAI/Ling-mini-2.0-GGUF: Same weights, converted
- bartowski/inclusionAI_Ling-mini-2.0-GGUF: Same weights, converted
- mradermacher/Ling-mini-2.0-i1-GGUF: Quantization
- voltaire321/Ming-Image-0.1-Design-GGUF: Different architecture
- redponike/Ling-mini-2.0-GGUF-ik: Quantization
- mradermacher/Ling-mini-2.0-GGUF: Quantization
- redponike/Ling-mini-2.0-GGUF: Quantization
- mlx-community/Ling-mini-2.0-4bit: Quantization
- qingy2024/Ling-Mini-2.0-Identity: Partial fine-tune
1 other repos hold byte-for-byte identical weight files.