Tiny-R1-32B-Preview, which outperforms the 70B model Deepseek-R1-Distill-Llama-70B and nearly matches the full R1 model in math.
1,705 Pulls 6 Tags Updated 1 year ago
A fine-tuned DeepSeek-R1-70B model for CVE-worthiness review, exploit-path analysis, and JSON-only vulnerability triage.
1,713 Pulls 1 Tag Updated 2 weeks ago
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.
85 Pulls 2 Tags Updated 1 month ago
29 Pulls 1 Tag Updated 1 year ago