CloudGoat/Orythos-9B
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-9B. CloudGoat/Orythos-9B matches part of Qwen/Qwen3.5-9B (431 of its 775 tensors; the rest of Qwen/Qwen3.5-9B 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 2/2, MLP 96/96, Attention 200/224, other 1/1, Norms 86/107
2 derivatives checked
- mradermacher/Orythos-9B-i1-GGUF: Quantization
- mradermacher/Orythos-9B-GGUF: Same weights, converted