Skip to content

Generate: update basic llm tutorial#26937

Merged
gante merged 1 commit intohuggingface:mainfrom
gante:batched_basic_docs
Oct 19, 2023
Merged

Generate: update basic llm tutorial#26937
gante merged 1 commit intohuggingface:mainfrom
gante:batched_basic_docs

Conversation

@gante
Copy link
Contributor

@gante gante commented Oct 19, 2023

What does this PR do?

This PR updates the basic LLM tutorial in the following aspects:

  1. Adds a short section right at the top on how to do batched generation. This was made to address How to perform batch inference?  #26061 (and other similar issues in the past)
  2. Updates the model used in the examples from OpenLlama (permissive licenses, but deprecated) to Mistral (latest 7B model with top performance and permissive licenses)
  3. Adds prompting to the list of common issues (was a TODO)
  4. Adds pointers to recent guides about prompting and performance

Fixes #26061

@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Oct 19, 2023

The documentation is not available anymore as the PR was closed or merged.

Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🚀 thanks for the cleanup

@gante gante merged commit ae4fb84 into huggingface:main Oct 19, 2023
@gante gante deleted the batched_basic_docs branch October 19, 2023 15:53
EduardoPach pushed a commit to EduardoPach/transformers that referenced this pull request Nov 19, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

How to perform batch inference?

3 participants