lhpku20010120/Omni-Edu-4B
Full fine-tune vs Qwen/Qwen3.5-4B-Base. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/4, MLP 96/196, Attention 190/320, Norms 70/203
1 derivatives checked
- prithivMLmods/Omni-Edu-4B-GGUF: Same weights, converted
2 other repos hold byte-for-byte identical weight files.