kaptaan45/QaptaanLM-0.75B
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-0.8B-Base. kaptaan45/QaptaanLM-0.75B matches part of Qwen/Qwen3.5-0.8B-Base (320 of its 488 tensors; the rest of Qwen/Qwen3.5-0.8B-Base has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Attention 134/168, Norms 30/79, Embeddings 1/1, MLP 72/72
2 derivatives checked
- kaptaan45/QaptaanLM-0.75B-GGUF: Same weights, converted
- kaptaan45/QaptaanLM-0.75B-Instruct: Partial fine-tune