NotEvilAI/gpt-oss-20b-ru-reasoner
Full fine-tune vs openai/gpt-oss-20b. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 2/49, MLP 88/96, Attention 192/216, lm_head 1/1, Embeddings 1/1
2 derivatives checked
- mradermacher/gpt-oss-20b-ru-reasoner-i1-GGUF: Quantization
- mradermacher/gpt-oss-20b-ru-reasoner-GGUF: Quantization