digitalneedstech/LLM Code Review

A container GitHub Action to review a pull request by HuggingFace LLM Model.

Trust Signals

Scorecard Score: not yet scored
Maintenance Recency: Stalelast commit Oct 24, 2024
License: None

Pinned Snippet

workflow.ymlSHA-pinned

uses: digitalneedstech/code-review-action@f820fb5fb4e0fb162d7b90414c2d5479558836a8 # 2

tags can be moved; commit SHAs can't. why a SHA?

Inputs

name	description	required	default
githubToken	Github token to access the repo	yes	—
apiKey	Huggingface access token from [https://huggingface.co/settings/tokens](https://huggingface.co/settings/tokens)	yes	—
githubRepository	The GitHub repository to use for the action	yes	${{ github.repository }}
githubPullRequestNumber	The GitHub pull request number to use for the action	yes	${{ github.event.pull_request.number }}
gitCommitHash	The GitHub commit hash to use for the action	yes	${{ github.event.pull_request.head.sha }}
repoId	LLM model	yes	meta-llama/Llama-2-7b-chat-hf
maxNewTokens	The amount of new tokens to be generated, this does not include the input length it is a estimate of the size of generated text you want. Each new tokens slows down the request, so look for balance between response times and length of text generated.	no	1024
temperature	The temperature of the sampling operation. 1 means regular sampling, 0 means always take the highest score, 100.0 is getting closer to uniform probability.	no	0.2
topK	Integer to define the top tokens considered within the sample operation to create new text	no	50
topP	Float to define the tokens that are within the sample operation of text generation. Add tokens in the sample for more probable to least probable until the sum of the probabilities is greater than top_p.	no	0.95
pullRequestDiff	Pull request diff	yes	—
pullRequestChunkSize	Pull request chunk size	no	3500
logLevel	Log level	no	INFO
accessKey	Access Key	yes	INFO
secretKey	Secret Key	yes	INFO
sessionToken	Session Token	yes	INFO

Outputs

no outputs