Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-21 23:57:58 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update 03 ‐ Parameters Tab.md

Browse Source
This commit is contained in:
oobabooga 2023-10-22 14:52:23 -03:00 committed by GitHub
parent 63688004dc
commit 7a3f885ea8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
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

@ -42,7 +42,7 @@ For more information about the parameters, the [transformers documentation](http
* **epsilon_cutoff**: In units of 1e-4; a reasonable value is 3. This sets a probability floor below which tokens are excluded from being sampled.
* **eta_cutoff**: In units of 1e-4; a reasonable value is 3. The main parameter of the special Eta Sampling technique. See [this paper](https://arxiv.org/pdf/2210.15191.pdf) for a description.
* **guidance_scale**: The main parameter for Classifier-Free Guidance (CFG). [The paper](https://arxiv.org/pdf/2306.17806.pdf) suggests that 1.5 is a good value. It can be used in conjunction with a negative prompt or not.
* **Negative prompt**: Only used when `guidance_scale != 1`. It is most useful for instruct models and custom system messages. You place your full prompt with the default system message for the model (like "You are Llama, a helpful assistant...") in this field to make the model pay more attention to your custom message.
* **Negative prompt**: Only used when `guidance_scale != 1`. It is most useful for instruct models and custom system messages. You place your full prompt in this field with the system message replaced with the default one for the model (like "You are Llama, a helpful assistant...") to make the model pay more attention to your custom system message.
* **penalty_alpha**: Contrastive Search is enabled by setting this to greater than zero and unchecking "do_sample". It should be used with a low value of top_k, for instance, top_k = 4.
* **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.