numind/NuExtract-1.5-tiny
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 11/49, MLP 72/72, Attention 151/168
6 derivatives checked
- abyrne55/nuextract-1.5-tiny-mealie-ingredient-parser: Full fine-tune
- mradermacher/NuExtract-1.5-tiny-i1-GGUF: Quantization
- nimendraai/NuExtract-tiny-Resume-Data-Extractor: Adapter
- featherless-ai-quants/numind-NuExtract-1.5-tiny-GGUF: Quantization
- mradermacher/NuExtract-1.5-tiny-GGUF: Same weights, converted
- DevQuasar-3/numind.NuExtract-tiny-v1.5-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.