ThakiCloud/Qwen3.8-27B-Human-KO
Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 92% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 0/325, Attention 304/560, MLP 192/307, Embeddings 0/5, lm_head 1/1, other 0/1
5 derivatives checked
- ThakiCloud/Qwen3.8-27B-Human-KO-MerchantDesk-v0.1: Full fine-tune
- ThakiCloud/Qwen3.8-27B-Human-KO-Enterprise-v0.1: Full fine-tune
- ThakiCloud/Qwen3.8-27B-Human-KO-Finance: Full fine-tune
- ThakiCloud/Qwen3.8-27B-Human-KO-NVFP4: Quantization
- ThakiCloud/Qwen3.8-27B-Human-KO-Enterprise-v0.2: Full fine-tune