Review of DeepSeek R1 Zero

#24
by nikitayev - opened

You can use it on OpenRouter: https://openrouter.ai/deepseek/deepseek-r1-zero:free

Register on the OpenRouter.ai website, and you’re ready to go.

The test task results are available here: https://disk.yandex.ru/d/eNQF9Fe0RtEwxg
The full folder of examples is here: https://disk.yandex.ru/d/iP_f37VTFKm_rA

I experimented with various settings, but the most interesting results came from:

  • Temperature: 0.6
  • Top P: 0.95
  • Top K: 100
  • Min P: 0.00

Examples with these settings are in the folders starting from:
2 without prompt, lenient conditions\variant 14
to
2 without prompt, lenient conditions\variant 18

The results for variants 14, 15, 16, and 17 are identical.

In fact, these outcomes are on par with those from today’s most advanced AI models.
The results could improve if Top_K could be increased.

Practical experience shows that higher Top_K values lead to better outputs—someone should shout this at all AI interface developers!
For example, in LM Studio, setting Top_K to 500 achieves superior results.


P.S.

Original: https://nikitayev.livejournal.com/157013.html

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment