iapp/OpenThai-SystemOne
Full fine-tune (fewer layers) vs Qwen/Qwen3.5-0.8B-Base. iapp/OpenThai-SystemOne matches part of Qwen/Qwen3.5-0.8B-Base (319 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 135/168, Norms 33/79, MLP 72/72
3 derivatives checked
- iapp/OpenThai-SystemOne-Ollama: Partial fine-tune
- iapp/OpenThai-SystemOne-GGUF: Same weights, converted (fewer layers)
- nectec/pathumma-crossborder-guardrail: Partial fine-tune