lucidrains/PaLM-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Pythonreinforcement-learningdeep-learningtransformersartificial-intelligenceattention-mechanismshuman-feedback
This is stars and forks stats for /lucidrains/PaLM-rlhf-pytorch repository. As of 24 Apr, 2024 this repository has 7317 stars and 624 forks.

official chatgpt blogpost PaLM + RLHF - Pytorch (wip) Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Maybe I'll add retrieval functionality too, à la RETRO If you are interested in replicating something like ChatGPT out in the open, please consider joining Laion Alternative: Chain of Hindsight FAQ Does this contain a model for inference? There is no trained model. This is just the ship and overall map. We still need millions of dollars of compute...
Read on GithubGithub Stats Page
repotechsstarsweeklyforksweekly
autonomousvision/sdfstudioPythonJavaScriptShell1.6k01510
giswqs/aws-open-data-geoPythonJupyter Notebook252070
google-research/frame-interpolationPython2.4k02410
tekakutli/anime_translationShellEmacs LispPython1230130
riscv-android-src/platform-build-bazelStarlarkShellPython0000
containers/crunCPythonMakefile2.5k02630
confluentinc/librdkafkaCC++Shell7k03.2k0
facebookexperimental/object-introspectionC++PythonCMake77090
edx/jenkins-configurationGroovyPythonMakefile1790540
sdiehl/write-you-a-haskellHaskellCSSOCaml3.3k-22620