Surpem/Supertron2-Reranker-8B

Partial fine-tune vs Qwen/Qwen3-VL-Reranker-8B. Partial change: 79% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/4, Norms 95/261, MLP 108/232, Attention 144/252, lm_head 0/1

3 derivatives checked

• mradermacher/Supertron2-Reranker-8B-i1-GGUF: Quantization (fewer layers)
• mradermacher/Supertron2-Reranker-8B-GGUF: Same weights, converted (fewer layers)
• seamon67/Supertron-2-Reranker-8B-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse