OpenMOSS-Team/SciJudge-30B

Partial fine-tune vs Qwen/Qwen3-30B-A3B-Instruct-2507. Partial change: 87% of the weights changed (attention, mlp, norms), in 48 of 48 layers.

Tensors changed: Embeddings 0/1, Norms 130/193, MLP 2543/2613, Attention 192/192, lm_head 0/1

1 derivatives checked

• mradermacher/SciJudge-30B-GGUF: Quantization

On the Hub · Downloads on Model Pulse