gpo.zugaina.org

Search Portage & Overlays:

dev-python/trl-fpo

Train transformer language models with reinforcement learning.

Screenshots

  • trl-fpo-0.0.15
    ~amd64 ~x86
    benchmark deepspeed dev diffusers llm-judge peft quantization test python_targets_python3_11 python_targets_python3_12 python_targets_python3_13 python_targets_python3_14

    View      Download      Browse     License: Apache-2.0   
    Overlay: pypi

USE Flags

benchmark
* This flag is undocumented *
deepspeed
* This flag is undocumented *
dev
* This flag is undocumented *
diffusers
* This flag is undocumented *
llm-judge
* This flag is undocumented *
peft
* This flag is undocumented *
quantization
* This flag is undocumented *
test
Global: Workaround to pull in packages needed to run with FEATURES=test. Portage-2.1.2 handles this internally, so don't set it in make.conf/package.use anymore
python_targets_python3_11
* This flag is undocumented *
python_targets_python3_12
* This flag is undocumented *
python_targets_python3_13
* This flag is undocumented *
python_targets_python3_14
* This flag is undocumented *