allenai/tmax-9b
Partial fine-tune (fewer layers) vs Qwen/Qwen3.5-9B. allenai/tmax-9b matches part of Qwen/Qwen3.5-9B (427 of its 775 tensors; the rest of Qwen/Qwen3.5-9B has no counterpart). On the shared part: Partial change: 77% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 96/96, Attention 178/224, Norms 61/105
2 derivatives checked
- ijohn07/tmax-9b-Q4_K_M-GGUF: Quantization
- mlx-community/Tmax-9B-MLX-4bit: Quantization
1 other repos hold byte-for-byte identical weight files.