moonshot
moonshot copied to clipboard
aiverify-foundation
Moonshot - A simple and modular tool to evaluate and red-team any LLM application.
1. Modified to allow multiple operations to be run at the same time. 2. Benchmark results files will have -.json 3. Red teaming is not tested yet. 4. Benchmark callback...
Hello team moonshot! We have been testing against our production Azure OpenAI endpoints and would like to share the following amendments. - Added a new `openai-azure.py` connector, this handles some...
With the current interactive CLI environment, we have to open a new terminal in order to run a new task (cookbook/recipe) concurrently. Would it be possible to run them in...
During model development, it can prove useful to have a safe exit sequence for a currently running task to make quick changes to the model and redeploy, instead of force...
For locally developed models / most models downloaded from HuggingfaceHub, it can be troublesome to set up an API endpoint for the model. There are libraries such as [vLLM](https://blog.vllm.ai/2023/06/20/vllm.html) that...
Metadata
Owner
Metadata
Moonshot - A simple and modular tool to evaluate and red-team any LLM application.