CodeGoat24/UnifiedReward-2.0-qwen35-4b
Full fine-tune vs Qwen/Qwen3.5-4B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 4/4, MLP 196/196, Attention 295/320, Norms 148/203
3 derivatives checked
- mradermacher/UnifiedReward-2.0-qwen35-4b-i1-GGUF: Quantization
- mradermacher/UnifiedReward-2.0-qwen35-4b-GGUF: Same weights, converted
- CodeGoat24/UnifiedReward-Edit-qwen35-4b: Partial fine-tune