mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Rename additive_repetition_penalty to presence_penalty, add frequency_penalty (#4376)

Browse source
This commit is contained in:
tdrussell 2023-10-25 10:10:28 -05:00 • committed by GitHub
parent ef1489cd4d
commit 72f6fc6923
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
14 changed files with 64 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

3
docs/03 ‐ Parameters Tab.md
View file

@ -35,7 +35,8 @@ For more information about the parameters, the [transformers documentation](http
* **top_p**: If not set to 1, select tokens with probabilities adding up to less than this number. Higher value = higher range of possible random results.
* **top_k**: Similar to top_p, but select instead only the top_k most likely tokens. Higher value = higher range of possible random results.
* **repetition_penalty**: Penalty factor for repeating prior tokens. 1 means no penalty, higher value = less repetition, lower value = more repetition.
* **additive_repetition_penalty**: Similar to repetition_penalty, but with an additive offset on the raw token scores instead of a multiplicative factor. It may generate better results. 0 means no penalty, higher value = less repetition, lower value = more repetition.
* **presence_penalty**: Similar to repetition_penalty, but with an additive offset on the raw token scores instead of a multiplicative factor. It may generate better results. 0 means no penalty, higher value = less repetition, lower value = more repetition. Previously called "additive_repetition_penalty".
* **frequency_penalty**: Repetition penalty that scales based on how many times the token has appeared in the context. Be careful with this; there's no limit to how much a token can be penalized.
* **repetition_penalty_range**: The number of most recent tokens to consider for repetition penalty. 0 makes all tokens be used.
* **typical_p**: If not set to 1, select only tokens that are at least this much more likely to appear than random tokens, given the prior text.
* **tfs**: Tries to detect a tail of low-probability tokens in the distribution and removes those tokens. See [this blog post](https://www.trentonbricken.com/Tail-Free-Sampling/) for details. The closer to 0, the more discarded tokens.