Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-25 09:19:23 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update docs

Browse Source
This commit is contained in:
oobabooga 2023-11-04 11:02:24 -07:00
parent 1d8c7c1fc4
commit fb3bd0203d
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/03 ‐ Parameters Tab.md
View File

@ -50,7 +50,7 @@ For more information about the parameters, the [transformers documentation](http
* **mirostat_mode**: Activates the Mirostat sampling technique. It aims to control perplexity during sampling. See the [paper](https://arxiv.org/abs/2007.14966). * **mirostat_mode**: Activates the Mirostat sampling technique. It aims to control perplexity during sampling. See the [paper](https://arxiv.org/abs/2007.14966).
* **mirostat_tau**: No idea, see the paper for details. According to the Preset Arena, 8 is a good value. * **mirostat_tau**: No idea, see the paper for details. According to the Preset Arena, 8 is a good value.
* **mirostat_eta**: No idea, see the paper for details. According to the Preset Arena, 0.1 is a good value. * **mirostat_eta**: No idea, see the paper for details. According to the Preset Arena, 0.1 is a good value.
* **temperature_last**: Makes temperature the last sampler instead of the first. With this, you can low probability tokens with a sampler like min_p and then use a high temperature to make the model creative without losing coherency. * **temperature_last**: Makes temperature the last sampler instead of the first. With this, you can remove low probability tokens with a sampler like min_p and then use a high temperature to make the model creative without losing coherency.
* **do_sample**: When unchecked, sampling is entirely disabled, and greedy decoding is used instead (the most likely token is always picked). * **do_sample**: When unchecked, sampling is entirely disabled, and greedy decoding is used instead (the most likely token is always picked).
* **Seed**: Set the Pytorch seed to this number. Note that some loaders do not use Pytorch (notably llama.cpp), and others are not deterministic (notably ExLlama v1 and v2). For these loaders, the seed has no effect. * **Seed**: Set the Pytorch seed to this number. Note that some loaders do not use Pytorch (notably llama.cpp), and others are not deterministic (notably ExLlama v1 and v2). For these loaders, the seed has no effect.
* **encoder_repetition_penalty**: Also known as the "Hallucinations filter". Used to penalize tokens that are *not* in the prior text. Higher value = more likely to stay in context, lower value = more likely to diverge. * **encoder_repetition_penalty**: Also known as the "Hallucinations filter". Used to penalize tokens that are *not* in the prior text. Higher value = more likely to stay in context, lower value = more likely to diverge.