OpenYourMind/OYM-Qimi-122B-A10B-K2.6
Partial fine-tune (fewer layers) vs Qwen/Qwen3.5-122B-A10B. Qwen/Qwen3.5-122B-A10B matches part of OpenYourMind/OYM-Qimi-122B-A10B-K2.6 (1853 of its 38717 tensors; the rest of OpenYourMind/OYM-Qimi-122B-A10B-K2.6 has no counterpart). On the shared part: Partial change: 70% of the weights changed (attention, mlp, norms, other), in 48 of 48 layers.
Tensors changed: lm_head 0/1, Embeddings 0/5, Attention 230/448, MLP 193/400, other 1/1, Norms 2/273
2 derivatives checked
- mradermacher/OYM-Qimi-122B-A10B-K2.6-GGUF: Quantization
- mradermacher/OYM-Qimi-122B-A10B-K2.6-i1-GGUF: Quantization