pragmaticcs/Triumvirate-Qwopus-MiMo-Ornith-9B-Coder
Full fine-tune (fewer layers) vs Jackrong/Qwopus3.5-9B-Coder. pragmaticcs/Triumvirate-Qwopus-MiMo-Ornith-9B-Coder matches part of Jackrong/Qwopus3.5-9B-Coder (427 of its 775 tensors; the rest of Jackrong/Qwopus3.5-9B-Coder has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, MLP 96/96, Attention 195/224, Norms 99/105
5 derivatives checked
- pragmaticcs/Triumvirate-Qwopus-MiMo-Ornith-9B-Coder-i1-GGUF: Quantization
- mradermacher/Triumvirate-Qwopus-MiMo-Ornith-9B-Coder-i1-GGUF: Quantization
- pragmaticcs/Triumvirate-Qwopus-MiMo-Ornith-9B-Coder-GGUF: Quantization
- mradermacher/Triumvirate-Qwopus-MiMo-Ornith-9B-Coder-GGUF: Same weights, converted
- alst10/Triumvirate-Qwopus-MiMo-Ornith-9B-Coder: Same weights, converted