OmniDimen/OmniDimen-2-20B-Emotion
Partial fine-tune vs openai/gpt-oss-20b. Partial change: 35% of the weights changed (attention, mlp), in 24 of 24 layers.
Tensors changed: Norms 0/49, MLP 20/96, Attention 96/216, lm_head 0/1, Embeddings 0/1
2 derivatives checked
- mradermacher/OmniDimen-2-20B-Emotion-i1-GGUF: Quantization
- mradermacher/OmniDimen-2-20B-Emotion-GGUF: Quantization