morganstanley/qqWen-32B-RL-Reasoning
Full fine-tune vs Qwen/Qwen2.5-32B-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 126/129, MLP 192/192, Attention 448/448, lm_head 1/1
3 derivatives checked
- gabriellarson/qqWen-32B-RL-Reasoning-GGUF: Same weights, converted
- mradermacher/qqWen-32B-RL-Reasoning-i1-GGUF: Quantization
- mradermacher/qqWen-32B-RL-Reasoning-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.