PoSTMEDIA/Vayne-V3-Pro

Full fine-tune vs openai/gpt-oss-safeguard-120b. Fine-tune: 96% of the weights changed, across 36 of 36 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, MLP 222/288, Norms 15/73, Attention 291/324

2 derivatives checked

• mradermacher/Vayne-V3-Pro-i1-GGUF: Quantization
• mradermacher/Vayne-V3-Pro-GGUF: Quantization

On the Hub · Downloads on Model Pulse