PyPI
huggingface/trl
Train transformer language models with reinforcement learning.
Apache-2.024 ago 2026 · métricas 2.10.0
Todas las etiquetas
Etiqueta del catálogo
#grpo
Todos los repositorios del registro público que llevan esta etiqueta, procedente de sus topics de GitHub o de las palabras clave que publican sus registros de paquetes. La salud se mide con la misma metodología versionada que el resto del registro.
8 registros
PyPI
PrimeIntellect-ai/verifiers
Our library for RL environments + evals
MIT28 ago 2026 · métricas 2.10.0
PyPI
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
Apache-2.027 ago 2026 · métricas 2.10.0
PyPI
hud-evals/hud-python
RL environments + evals for AI agents. Define once, train anything.
MIT20 sept 2026 · métricas 2.10.0
PyPI
JudgmentLabs/judgeval
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
Apache-2.017 sept 2026 · métricas 2.10.0
PyPI
freesolo-co/flash
LoRA post-training for open-weight models: SFT, GRPO, and on-policy distillation. Describe a run in TOML; Flash allocates a GPU, trains, streams checkpoints, and serves the adapter.
Apache-2.021 oct 2026 · métricas 2.10.0
PyPI
whilehq/whileai-sdk
While Python SDK (formerly zeroproof): trace ingest, agent simulations, grading, and training data for post-training
Apache-2.018 sept 2026 · métricas 2.10.0
PyPI
waybarrios/crystal
CRYSTAL: Beyond Final Answers: Benchmark for Transparent Multimodal Reasoning Evaluation | arXiv 2603.13099
Sin licencia17 jul 2026 · métricas 2.10.0