gspo

Here are 8 public repositories matching this topic...

Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.

opd retool opsd gspo alfworld dapo search-r1 agent-rl pytrio harness-rl

Reinforcement learning for text generation on MLX (Apple Silicon)

reinforcement-learning text-generation lora mlx apple-silicon gspo qlora mlx-lm grpo

Sync vs fully-async agentic RL on verl: multi-turn GRPO, long-tail rollout profiling, staleness ablations — quantifying when async pays off.

reinforcement-learning rollout slime post-training multi-turn megatron gspo llm-agent tool-calling verl dapo agentic-rl async-training

Training and dataset-building pipeline for NVIDIA Nemotron reasoning experiments using Unsloth, TRL and NeMo RL.

rl sft dpo trl llm gspo unsloth nvidia-nemotron nemo-rl

Medical multi-agent assistant, Qwen3.5-2B LoRA SFT and GSPO experiments, with public datasets and adapters on Hugging Face.

multi-agent lora sft huggingface medical-ai gspo qwen

OPSG-based test refinement for Java: Stable RL approach to generate maintainable, high-quality unit tests with 98.6% compilation success.

CS336A5 小显存适配：用小显卡直接进行 OLMo-2 全参数强化学习训练，已在单张 RTX 5070 Ti 16GB 上验证。提供低显存训练配置、vLLM 批量生成与复现说明。

reinforcement-learning memory-efficient cs336 gspo vllm olmo grpo rtx-5070-ti

RL agents across LangChain & LangGraph, 50+ MCP registry tools, PGVector stores, deployment w Dynamo and inference with vLLM & SGLang

To associate your repository with the gspo topic, visit your repo's landing page and select "manage topics."