Surpem/Supertron2-Reranker-2B

Partial fine-tune vs Qwen/Qwen3-VL-Reranker-2B. Partial change: 66% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/4, Norms 84/217, MLP 84/196, Attention 112/208

3 derivatives checked

• mradermacher/Supertron2-Reranker-2B-i1-GGUF: Quantization (fewer layers)
• mradermacher/Supertron2-Reranker-2B-GGUF: Same weights, converted (fewer layers)
• seamon67/Supertron-2-Reranker-2B-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse