Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feature/toploc-integration #127

Merged
merged 29 commits into from
Mar 10, 2025
Merged

feature/toploc-integration #127

merged 29 commits into from
Mar 10, 2025

Conversation

JannikSt
Copy link
Member

@JannikSt JannikSt commented Feb 26, 2025

Simple way to test this:
Run make up

Start a worker make watch-worker

execute test script in python folder:
python3 work_validation.py

you should see the most recent validation key appear on the validator log panel

Start leviticus container on remote machine (validation works):

docker run -d --gpus all -p 8000:8000 \
	-e GCP_CREDENTIALS=$GCP_CREDENTIALS \
	primeintellect/leviticus:latest \
	--model-path Qwen/Qwen2.5-Coder-0.5B \
	--gcp-path protocol-development-bucket 

Other model - validation fails:

docker run -d --gpus all -p 8001:8000 \
	-e GCP_CREDENTIALS=$GCP_CREDENTIALS \
	primeintellect/leviticus:latest \
        --model-path deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B \
	--gcp-path protocol-development-bucket 

@JannikSt JannikSt requested a review from mattdf February 26, 2025 16:48
@JannikSt
Copy link
Member Author

JannikSt commented Mar 6, 2025

we actually have to fix #118 also - atm the orchestrator never learns that one of their nodes was already rejected. Same applies for the discovery service @mattdf

@JannikSt JannikSt merged commit 36bb005 into develop Mar 10, 2025
1 check passed
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.

2 participants