VaalaCat/go-openai
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Doc ways to improve reproducability besides Temp (#532)

Browse Source
This commit is contained in:
Carson Kahn
2023-11-07 04:27:29 -05:00
committed by GitHub
parent 0664105387
commit d07833e19b
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@@ -757,8 +757,9 @@ Even when specifying a temperature field of 0, it doesn't guarantee that you'll
Due to the factors mentioned above, different answers may be returned even for the same question. Due to the factors mentioned above, different answers may be returned even for the same question.
**Workarounds:** **Workarounds:**
1. Using `math.SmallestNonzeroFloat32`: By specifying `math.SmallestNonzeroFloat32` in the temperature field instead of 0, you can mimic the behavior of setting it to 0. 1. As of November 2023, use [the new `seed` parameter](https://platform.openai.com/docs/guides/text-generation/reproducible-outputs) in conjunction with the `system_fingerprint` response field, alongside Temperature management.
2. Limiting Token Count: By limiting the number of tokens in the input and output and especially avoiding large requests close to 32k tokens, you can reduce the risk of non-deterministic behavior. 2. Try using `math.SmallestNonzeroFloat32`: By specifying `math.SmallestNonzeroFloat32` in the temperature field instead of 0, you can mimic the behavior of setting it to 0.
3. Limiting Token Count: By limiting the number of tokens in the input and output and especially avoiding large requests close to 32k tokens, you can reduce the risk of non-deterministic behavior.
By adopting these strategies, you can expect more consistent results. By adopting these strategies, you can expect more consistent results.