aisingapore/Qwen-SEA-LION-v4.5-27B-IT
Partial fine-tune vs Qwen/Qwen3.6-27B. Partial change: 74% of the weights changed (attention, lm_head, mlp, norms), in 64 of 64 layers.
Tensors changed: Embeddings 0/5, MLP 158/307, Attention 269/560, lm_head 1/1, Norms 68/325, other 0/1
2 derivatives checked
- toeniant/Qwen-SEA-LION-v4.5-27B-IT-FP8-Dynamic: Quantization
- aisingapore/Qwen-SEA-LION-v4.5-27B-IT-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.