huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: improve image for dark and light mode

Browse Source
This commit is contained in:
drbh 2024-04-30 13:27:25 -04:00
parent 8a417da317
commit 43a43fdfbc
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docs/source/conceptual/guidance.md
View File

@ -23,11 +23,6 @@ However these use cases can span a wide range of applications, such as:
- provide reliable and consistent output for downstream tasks - provide reliable and consistent output for downstream tasks
- extract data from multimodal inputs - extract data from multimodal inputs
<div class="flex justify-center">
<img
src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/multimodal-guidance.png"
/>
</div>
## How it works? ## How it works?
@ -42,8 +37,13 @@ This process can be broken down into the following steps:
<div class="flex justify-center"> <div class="flex justify-center">
<img <img
class="block dark:hidden"
src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/logit-grammar-mask.gif" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/logit-grammar-mask.gif"
/> />
<img
class="hidden dark:block"
src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/logit-grammar-mask-dark.gif"
/>
</div> </div>
4. The grammar mask is applied and the model samples from the remaining tokens. Once a token is chosen, we update the grammar state with the new token, to prepare it for the next pass. 4. The grammar mask is applied and the model samples from the remaining tokens. Once a token is chosen, we update the grammar state with the new token, to prepare it for the next pass.