56 skills · sorted by relevance
Prepare GRPO reinforcement learning configurations for tasks with programmatically checkable answers, such as math, code, and structured output. Design and inspect reward functions, then select training variants when runs show instability or exploit flaws in scoring.
Set up reinforcement learning, which trains models using rewards, with verl. Follow workflows for preparing data, configuring GRPO or PPO training, scaling across GPUs, and addressing memory errors or unstable training.
Plan and configure large language model training with OpenRLHF to better match human preferences. Covers training method selection, distributed GPU setup, inference acceleration with vLLM, and troubleshooting memory or training stability issues.
Guides language model training with GRPO in TRL, comparing several responses and rewarding better results. Covers dataset preparation, scoring rules for correctness and format, training configuration, monitoring, and saving models for later use.
Guides LLM training with verl using rewards to improve model responses. Covers data preparation, reward functions, GRPO and PPO configuration, distributed GPU training, and troubleshooting memory shortages or unstable training.
Set up model training with torchforge for reinforcement learning, where rewards guide improvement. Covers training configurations, custom reward and loss functions, and distributed execution with Monarch and TorchTitan, keeping algorithm experiments separate from infrastructure concerns.
Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.
Guides reinforcement learning, where models learn from rewards, using torchforge and PyTorch. Covers reward design, custom loss functions, and distributed training so researchers can experiment with algorithms while keeping infrastructure concerns separate.
Guide large language model training with OpenRLHF using human preference feedback. Covers training method selection, distributed GPU setup, reward model training, and memory tuning, with examples for PPO, GRPO, and DPO.
Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.
Guide language model training with TRL using example answers, preferred response pairs, or reward scores. The skill covers data preparation, method selection, reward model training, evaluation, and adjustments for memory limits or unstable training.
Fine-tune language models with TRL using GRPO, a method that compares scored responses to the same prompt. Covers training data, scoring functions, GPU-conscious settings, and monitoring for tasks with measurable correctness or required output formats.
Set up reinforcement learning, training guided by rewards, for language models with slime. The skill covers Megatron-LM training, SGLang response generation, data preparation, asynchronous execution, and custom workflows for agents that use tools across multiple turns.
Set up reinforcement learning, training guided by response rewards, for large language models. Use Megatron-LM and SGLang to prepare data, configure training and response generation, and build asynchronous or multi-turn experiments.
Guide reinforcement learning, training models through rewards, with slime. Prepare data, configure Megatron-LM training and SGLang response generation, and set up asynchronous runs or custom multi-turn workflows for supported language models.
基于ark_sdk的大模型训练任务自动化工具。帮助用户通过自然语言创建并提交方舟模型训练任务，支持用户自备数据的SFT训练、RFT+GRPO和直接GRPO策略，并引导用户完成训练、状态跟踪与评估闭环。使用场景：当用户需要进行大模型SFT监督微调、RLHF训练、GRPO训练、RFT训练，或需要自动化训练流程时触发。
The English summary is being prepared. Showing the original description.
Get guidance for fine-tuning large language models with Axolotl, adapting them through additional training. Use YAML configuration examples, dataset references, and training methods such as LoRA to set up training and investigate problems.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Reference for the GRPO (Group Relative Policy Optimization) algorithm. Use when implementing, debugging, or verifying a GRPO training pipeline — covers the mathematical formulation (group-relative advantages, clipped surrogate loss, KL penalty), the training loop (generate → score → advantage → loss), log-probability computation, advantage estimation, and relationship to PPO/REINFORCE.
The English summary is being prepared. Showing the original description.
Orientação especializada para ajuste fino com GRPO/RL usando TRL para treinamento de modelos com raciocínio e tarefas específicas
The English summary is being prepared. Showing the original description.
Set up and run reinforcement learning with verifiable rewards (RLVR/GRPO) for math, code, or custom environments using the Tinker API. Use when the user wants to do RL training, GRPO, reward-based optimization, or train with verifiable rewards.
The English summary is being prepared. Showing the original description.
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
The English summary is being prepared. Showing the original description.
Plan further training for AI agent models by diagnosing gaps in knowledge, output consistency, or decision making. Compare continued pretraining, supervised fine-tuning, reinforcement learning, and distillation, then design training data, feedback environments, and evaluation checks.