A fine-tuned DeepSeek-R1-70B model for CVE-worthiness review, exploit-path analysis, and JSON-only vulnerability triage.
Thai reasoning model that shows its step-by-step thinking — beats DeepSeek R1 70B and Typhoon R1 70B on Thai benchmarks (avg 71.58 vs 63.31/65.42) at half their size. ~24 GB RAM.