issai/Qwen3.5-9B-Kazakh
Full fine-tune (fewer layers) vs issai/Qwen3.5-9B-Base-Kazakh. issai/Qwen3.5-9B-Base-Kazakh matches part of issai/Qwen3.5-9B-Kazakh (427 of its 760 tensors; the rest of issai/Qwen3.5-9B-Kazakh 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, Norms 87/105, Attention 197/224, MLP 96/96
1 derivatives checked
- mradermacher/Qwen3.5-9B-Kazakh-GGUF: Same weights, converted