kprsnt/BrandXY-gpt-oss-20b

Full fine-tune vs openai/gpt-oss-20b. Fine-tune: 98% of the weights changed, across 24 of 24 layers.

Tensors changed: Norms 0/49, MLP 53/96, Attention 187/216, lm_head 1/1, Embeddings 1/1

2 derivatives checked

• mradermacher/BrandXY-gpt-oss-20b-i1-GGUF: Quantization
• mradermacher/BrandXY-gpt-oss-20b-GGUF: Quantization

On the Hub · Downloads on Model Pulse