lightblue/lb-reranker-0.5B-v1.0
Full fine-tune vs Qwen/Qwen2.5-0.5B-Instruct. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 168/168
3 derivatives checked
- bartowski/lb-reranker-0.5B-v1.0-GGUF: Same weights, converted
- DevQuasar-6/lightblue.lb-reranker-0.5B-v1.0-GGUF: Same weights, converted
- mradermacher/lb-reranker-0.5B-v1.0-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.