nvidia/Qwen3-Nemotron-235B-A22B-GenRM-2603

Full fine-tune vs Qwen/Qwen3-235B-A22B-Thinking-2507. Fine-tune: 100% of the weights changed, across 94 of 94 layers.

Tensors changed: Embeddings 1/1, MLP 2241/2245, Norms 229/377, Attention 376/376, lm_head 1/1

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse