RLVR-SvS/SvS-Qwen-3B
Partial fine-tune vs Qwen/Qwen2.5-3B-Instruct. Partial change: 90% of the weights changed (attention, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 59/73, MLP 108/108, Attention 252/252
2 derivatives checked
- mradermacher/SvS-Qwen-3B-i1-GGUF: Quantization
- mradermacher/SvS-Qwen-3B-GGUF: Same weights, converted