Qwen/Qwen3Guard-Stream-0.6B

Partial fine-tune vs Qwen/Qwen3-0.6B. Partial change: 74% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 102/113, MLP 84/84, Attention 112/112

2 derivatives checked

• geoffmunn/Qwen3Guard-Stream-0.6B: Quantization
• zenlm/zen-guard-stream: Identical copy

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

On the Hub · Downloads on Model Pulse