Pinned Loading
-
openai/evals
openai/evals PublicEvals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
-
summarizing-from-human-feedback
summarizing-from-human-feedback PublicImplementation of OpenAI's "Learning to Summarize with Human Feedback"
-
bitblaster-16
bitblaster-16 PublicBitBlaster-16 is a 16-bit computer built from scratch using only NAND gates and data flip-flops as primitives! :)
Python 2
-
fermi-poker
fermi-poker PublicLearn how to quantify your uncertainty by playing Fermi poker!
Python 3
-
self-taught-critiquer
self-taught-critiquer PublicReducing the time to create critique-writing models by 100-1000x on n-digit arithmetic problems by getting the model to learn from its own generated outputs.
Python 1
-
A PyTorch hook that's registered in...
A PyTorch hook that's registered in a `with` statement 1# This hook is particularly useful when ablating layers
23class ContextHook:
4def __init__(self, layer):
5self.layer = layer
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.