Jackrong/Negentropy-claude-opus-4.7-9B
Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 61% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/4, MLP 96/208, Attention 56/332, Norms 24/215
4 derivatives checked
- mradermacher/Negentropy-claude-opus-4.7-9B-i1-GGUF: Quantization
- mradermacher/Negentropy-claude-opus-4.7-9B-GGUF: Same weights, converted
- OliviaRossi/MiMo-Negentropy-9B-AGSI: Full fine-tune
- OliviaRossi/MiMo-Negentropy-9B-AGSI-GGUF: Full fine-tune