OpenWebRL/OpenWebRL-9B-SFT

Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 84% of the weights changed (attention, lm_head, mlp, norms), in 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 0/4, MLP 96/208, Attention 182/332, Norms 67/215

1 derivatives checked

• mradermacher/OpenWebRL-9B-SFT-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse