numind/NuExtract-tiny

Full fine-tune vs Qwen/Qwen1.5-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Embeddings 1/1, Norms 11/49, MLP 72/72, Attention 168/168

2 derivatives checked

• mradermacher/NuExtract-tiny-GGUF: Same weights, converted
• DevQuasar-3/numind.NuExtract-tiny-GGUF: Quantization

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse