“rlh”的搜索结果

This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.

中文简介正在准备中。当前显示原文说明。

Fine-tunes LLMs and trains custom models using LoRA/QLoRA adapters, JSONL training datasets, hyperparameter configuration, RLHF, DPO, and model quantization.

中文简介正在准备中。当前显示原文说明。

Design a complete document-based history lesson using the Reading Like a Historian four-part structure. Use when planning a primary source inquiry lesson or converting a textbook lesson into document-based investigation.

中文简介正在准备中。当前显示原文说明。

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。

中文简介正在准备中。当前显示原文说明。

Trigger this skill when the user wants to train, fine-tune, or adapt Gemma models (e.g. SFT, DPO, RLHF, Reward Modeling) on local hardware. Covers TRL, Unsloth, dataset preparation, validation, and GGUF/LiteRT conversion.

中文简介正在准备中。当前显示原文说明。

Design a complete document-based history lesson using the Reading Like a Historian four-part structure. Use when planning a primary source inquiry lesson or converting a textbook lesson into document-based investigation.

中文简介正在准备中。当前显示原文说明。

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

中文简介正在准备中。当前显示原文说明。

Orientação especializada para ajuste fino com GRPO/RL usando TRL para treinamento de modelos com raciocínio e tarefas específicas

中文简介正在准备中。当前显示原文说明。

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

中文简介正在准备中。当前显示原文说明。

Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.

中文简介正在准备中。当前显示原文说明。

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

中文简介正在准备中。当前显示原文说明。