tngtech/DeepSeek-TNG-R1T2-Chimera
Full fine-tune vs deepseek-ai/DeepSeek-R1. Fine-tune: 100% of the weights changed, across 62 of 62 layers.
Tensors changed: Embeddings 2/2, Attention 620/620, Norms 221/252, MLP 2123/2123, lm_head 1/1, other 2/2
3 derivatives checked
- unsloth/DeepSeek-TNG-R1T2-Chimera-GGUF: Quantization
- DevQuasar/tngtech.DeepSeek-TNG-R1T2-Chimera-GGUF: Quantization
- ubergarm/DeepSeek-TNG-R1T2-Chimera-GGUF: Quantization