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

Fix #320. Reuse the asyncio loop between sync calls #336

Merged
merged 1 commit into from
Feb 16, 2024

Conversation

drazvan
Copy link
Collaborator

@drazvan drazvan commented Feb 16, 2024

Other components might cache it, like openai and it would break things.

@drazvan drazvan merged commit 0ddbf54 into develop Feb 16, 2024
4 checks passed
ProKil added a commit to sotopia-lab/sotopia that referenced this pull request May 27, 2024
ProKil added a commit to sotopia-lab/sotopia that referenced this pull request Jun 17, 2024
* add benchmark social agents

* add benchmark agents

* Add sotopia_benchmark cli api

* fix pre-commit

* add evaluator model argument

* finish benchmarking

* benchmark done

* chore: Fix formatting issue in redis_stats.ipynb and cli.py

* switch back to LLM_Name

* merge main

* add together ai

* fix naming error

* roll back to llama2

* chore: Update langchain-together dependency to version 0.1.2

* use chatopenai for together models

* add logging

* fix pre-commit

* add more logging options

* probably fix the event loop closed error: following NVIDIA/NeMo-Guardrails#336

* modify cli; fix model position bug

* chore: Update benchmark tag to "benchmark_{model}_final"

* Refactor _iterate_all_env_agent_combo_not_in_db function

* chore: Update python version to 3.11.2

* change to dict comparison

* ignore jsonl

* ✨ finish benchmarking script

* chore: Refactor server.py and redis_stats.ipynb

* add type ignore

* push for the eval

* Refactor run_async_benchmark_in_batch function

* Refactor run_async_benchmark_in_batch function

* add doc

* precommit fix

* pre-commit

* refactor

* update w feedback

* pre commit

* chore: Update authors in pyproject.toml and fetch benchmark_agents.json from Hugging Face API

* hotfix

* chore: Remove unnecessary type hint in benchmark/cli.py

---------

Co-authored-by: Hao <prokilchu@gmail.com>
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.

1 participant