动态

(无标题)

(无标题)
elie
very interesting table from deepseek v3.2 that compares the output token count on different benchmarks, dsv3.2 speciale version thinks much more than any other model, BUT since they are using sparse attention the inference cost will still be ok? https://t.co/qc0iu4nx5A
动态Andrew Curran2025-12-01原文

相关内容