CodeGoat24/UnifiedReward-2.0-qwen-3b
Partial fine-tune vs Qwen/Qwen2.5-VL-3B-Instruct. Partial change: 82% of the weights changed (attention, embeddings, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 1/2, Norms 72/138, MLP 108/304, Attention 252/380
2 derivatives checked
- mradermacher/UnifiedReward-2.0-qwen-3b-i1-GGUF: Full fine-tune (fewer layers)
- mradermacher/UnifiedReward-2.0-qwen-3b-GGUF: Full fine-tune (fewer layers)