CodeGoat24/UnifiedReward-2.0-qwen3vl-8b
Partial fine-tune vs Qwen/Qwen3-VL-8B-Instruct. Partial change: 88% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 1/4, Norms 131/261, MLP 120/232, Attention 144/252, lm_head 1/1
4 derivatives checked
- mradermacher/UnifiedReward-2.0-qwen3vl-8b-i1-GGUF: Quantization (fewer layers)
- mradermacher/UnifiedReward-2.0-qwen3vl-8b-GGUF: Same weights, converted (fewer layers)
- CodeGoat24/UnifiedReward-Think-qwen3vl-8b: Partial fine-tune
- CodeGoat24/UnifiedReward-Edit-qwen3vl-8b: Partial fine-tune