CodeGoat24/UnifiedReward-Think-qwen3vl-8b
Partial fine-tune vs CodeGoat24/UnifiedReward-2.0-qwen3vl-8b. Partial change: 86% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 1/4, Norms 132/261, MLP 108/232, Attention 144/252, lm_head 1/1
3 derivatives checked
- mradermacher/UnifiedReward-Think-qwen3vl-8b-i1-GGUF: Quantization (fewer layers)
- mradermacher/UnifiedReward-Think-qwen3vl-8b-GGUF: Same weights, converted (fewer layers)
- CodeGoat24/UnifiedReward-Flex-qwen3vl-8b: Partial fine-tune