ddwang2000/EmotionThinker
Partial fine-tune (fewer layers) vs Qwen/Qwen2.5-Omni-7B. ddwang2000/EmotionThinker matches part of Qwen/Qwen2.5-Omni-7B (1346 of its 2448 tensors; the rest of Qwen/Qwen2.5-Omni-7B has no counterpart). On the shared part: Partial change: 81% of the weights changed (attention, lm_head, mlp, norms, other), in 32 of 32 layers.
Tensors changed: other 1/7, MLP 84/408, Norms 53/252, Attention 292/676, Embeddings 0/2, lm_head 1/1
1 other repos hold byte-for-byte identical weight files.