'sft' 검색 결과

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a training approach for an agent model
• Designing training examples and source data
• Planning reward checks and reinforcement learning environments

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback

TRL로 언어 모델을 추가 학습해 지시와 사람의 선호에 맞는 답변을 만들도록 안내합니다. 데이터 준비, 학습 방식 선택, 보상 모델 학습과 평가를 다룹니다.

• 답변 예시로 지시 수행을 학습합니다
• DPO로 답변 선호를 학습합니다
• 보상 모델을 쓰는 RLHF를 구성합니다

Turn graded execution traces and production logs into model training examples and preferred-versus-rejected response pairs. Select useful records, remove sensitive information, exclude evaluation examples, and preserve links to the original runs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Convert high-scoring successful runs into training examples
• Use expert-corrected failures as training examples
• Pair passing and failing responses to the same task

Prepare and review LoRA or QLoRA settings for adapting language models using example responses. Choose trainable layers, adapter capacity, learning rate, and memory-related options, then produce configuration values for a downstream training script.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a LoRA configuration for supervised fine-tuning
• Reviewing rank, alpha, and learning rate settings
• Choosing LoRA or QLoRA based on GPU memory

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Training a language model on example responses
• Training with preferred and rejected response pairs
• Debugging GRPO reward functions and batch settings

Turn ePub books into training examples for models that reproduce an author's writing style. Covers text extraction, coherent segmentation, varied instructions, model training, and checks for copied phrases and style transfer to new scenarios.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build training datasets from ePub books
• Train a model on an author's writing style
• Check for copied phrases in generated prose

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Training a language model on example responses
• Training with preferred and rejected response pairs
• Debugging GRPO reward functions and batch settings

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

Prepare datasets for language model training by formatting examples, checking conversation templates, and packing examples into training sequences. Document data sources, synthetic data ratios, and validation results in a dataset card before starting a run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Convert raw examples into training-ready JSONL
• Check conversation templates and assistant-only training targets
• Review example boundaries after sequence packing

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

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。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Post-train LLMs with PrimeIntellect's prime-rl (async RL, SFT, distillation, evals). Use this skill whenever the user mentions prime-rl, wants to write an rl.toml or sft.toml, run `uv run rl` / `uv run sft` / `uv run eval` / `uv run inference`, pick GRPO, MaxRL, OPD or ECHO, tune IPO loss, or monitor and resume a run. Also trigger for verifiers environments, Prime Intellect post-training, reverse-text, and pydantic-config TOML overrides.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train mathematical reasoning models with GRPO
• Experiment with custom reward and loss functions
• Scale training across multiple GPUs or nodes

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train mathematical reasoning models with GRPO
• Experiment with custom loss functions
• Scale training across multiple GPUs or nodes

Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Train and run models on Tinker (Thinking Machines) — LoRA and full fine-tuning, SFT with correct loss masking, RL/RFT with group-relative advantages and importance sampling, agentic RL over multi-turn tool-using agents, inference via the SamplingClient or the OpenAI-compatible endpoint, checkpoint management and export, every hyperparameter, and cost estimation from the live price table. Use this skill whenever the user mentions Tinker, tinker://, TINKER_API_KEY, console.tinker.ai, or the tinker CLI; wants to fine-tune, SFT, RFT, or RL a model on Tinker; asks about Tinker models, context windows, LoRA rank, sampling params, loss functions (cross_entropy, importance_sampling, ppo, cispo, dro), Datum construction, forward_backward or optim_step; wants to sample from, download, resume, merge, or export a Tinker checkpoint; or asks what a Tinker run will cost. Whenever Tinker work is initialized in a project, this skill also creates a TINKER_PRICING.md there so prices sit next to the training code. Reach for it even on vague asks like "train a model on this data" or "get inference working" when Tinker is the platform in play.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when a task requires SSH or SCP/SFTP behavior, a remote server, server alias/IP/hostname/user@host, bastion or jump-host access, remote command execution, upload/download, server transfer, deployment, tunnels, port forwarding, or remote internal services; Chinese triggers include 服务器, 远程, 连接, 登录, 上传, 下载, 部署, 跳板机, 隧道. DO NOT use for local shell commands, localhost/current-machine work, local Docker, browser downloads, Git remotes, or direct non-SSH database access.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Work with BioReason-Pro predictions and reasoning traces for protein function. Use when: comparing BioReason outputs against curated reviews, converting web exports to YAML, reviewing reasoning trace quality, or running the SFT/RL comparison. Triggers: "bioreason", "GO-GPT predictions", "reasoning trace review", "bioreason comparison", "SFT vs RL".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Prepare high-quality datasets for LLM fine-tuning with filtering, deduplication, augmentation, and RLHF data formatting. Activate on: fine-tuning data, training data curation, RLHF dataset, data quality filtering, SFT dataset. NOT for: model training infrastructure (ai-engineer), prompt engineering without fine-tuning (prompt-engineer).

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.