'grpo' 검색 결과

Decide whether an LLM needs additional training or whether retrieval and better prompts will suffice. Match available examples, preferences, or verifiable results to a training method, then assess model size and memory requirements before starting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing fine-tuning with retrieval and prompt changes
• Choosing a training method for available data
• Assessing model size and memory requirements

Get guidance on adapting large language models with Axolotl. Covers YAML configuration files, LoRA and QLoRA methods for training fewer parameters, distributed training settings, dataset formats, and debugging training code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Write YAML settings for model fine-tuning
• Explore training with LoRA or QLoRA
• Configure training across multiple GPUs

Guides LLM fine-tuning with Axolotl, from YAML configuration and dataset formats to distributed training across GPUs. Covers LoRA and QLoRA, methods that train on preferences, multimodal support, and troubleshooting using documentation references and code examples.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare YAML settings for LLM fine-tuning
• Explore LoRA, QLoRA, and preference training options
• Check dataset formats and input handling

Train or fine-tune language and vision models on Hugging Face Jobs without a local GPU. Covers dataset checks, hardware and cost planning, training monitoring, Hub storage, and GGUF conversion for local use.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tune a language model without a local GPU
• Validate preference data before DPO training
• Estimate training costs and choose GPU hardware

Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Ajuste fino de LLMs usando reinforcement learning com TRL - SFT para ajuste de instruções, DPO para alinhamento de preferências, PPO/GRPO para otimização de recompensas e treinamento de modelo de recompensas. Use quando precisar de RLHF, alinhar modelo com preferências ou treinar a partir de feedback humano. Funciona com HuggingFace Transformers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Fornece orientação para treinar LLMs com aprendizado por reforço usando verl (Volcano Engine RL). Use ao implementar RLHF, GRPO, PPO ou outros algoritmos de RL para pós-treinamento de LLMs em escala com backends de infraestrutura flexíveis.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Framework RLHF de alta performance com aceleração Ray+vLLM. Use para treinamento PPO, GRPO, RLOO, DPO de modelos grandes (7B-70B+). Construído em Ray, vLLM, ZeRO-3. 2× mais rápido que DeepSpeedChat com arquitetura distribuída e compartilhamento de recursos GPU.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Orientação especializada para fine-tuning de LLMs com Axolotl - configs YAML, 100+ modelos, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, suporte multimodal

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design rewards for reinforcement learning, where feedback guides model behavior. Choose how to score outcomes and intermediate actions, check for scoring loopholes, and use independent tests to detect incomplete work presented as finished.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing rewards for reinforcement learning
• Investigating scoring loopholes and early completion
• Choosing outcome rewards or intermediate feedback

Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Reference for the TRL (Transformer Reinforcement Learning) library codebase. Use proactively before reading or editing any file under `trl/` so you have the intended contracts and invariants in mind, not just what the current code says. Covers trainer hierarchy (SFT, DPO, GRPO, KTO), shared utility functions (selective_log_softmax, decode_and_strip_padding, padding helpers), configuration system, model wrappers, and how data flows through any TRL trainer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Diagnostic guide for RL-based post-training of language models (GRPO, PPO, REINFORCE, DPO). Use proactively when debugging a training pipeline that shows no improvement, loss anomalies, reward stagnation, NaN gradients, or other unexpected behavior during reinforcement learning fine-tuning. Work through all pipeline stages — reward, advantages, log-probs, loss, generation/decoding — before concluding the diagnosis is complete; stopping after one or two fixes is a common failure mode. Covers log-probability math, advantage estimation, numerical stability, reward processing, and generation/decoding pipeline issues.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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/.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Routes agents working with Axolotl config-driven LLM fine-tuning, datasets, SFT, preference tuning, GRPO/EBFT, model adapters, distributed training, CLI operations, and troubleshooting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Chooses DPO, GRPO/RLVR, reward models, and over-optimization controls. Use when adapting a pretrained or SFT model with preference or verifiable reward signals.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.