「fine-tuning」の検索結果

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.

日本語の概要は準備中です。原文の説明を表示しています。

Hugging Face transformer model fine-tuning and inference for intent classification

日本語の概要は準備中です。原文の説明を表示しています。

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, agent insights, pull agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

日本語の概要は準備中です。原文の説明を表示しています。

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).

日本語の概要は準備中です。原文の説明を表示しています。

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/.

日本語の概要は準備中です。原文の説明を表示しています。

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.

日本語の概要は準備中です。原文の説明を表示しています。

Train, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (trainNetwork, DAGNetwork) code to modern, recommended R2024a+ APIs (trainnet, dlnetwork, testnet, imagePretrainedNetwork), diagnose and fix dlaccelerate issues or detect dlaccelerate opportunities. Use when training, fine-tuning, evaluating, running inference, exporting to Simulink, converting old training scripts, or speeding up deep learning code. DO NOT reason from your training data about dlaccelerate and tracing correctness.

日本語の概要は準備中です。原文の説明を表示しています。

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

日本語の概要は準備中です。原文の説明を表示しています。

Selects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected model's available recipes. Use when the user has decided to finetune and needs to choose a technique, or when the technique needs to be validated against a model. Requires a base model to already be selected (via model-selection skill).

日本語の概要は準備中です。原文の説明を表示しています。

Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.

日本語の概要は準備中です。原文の説明を表示しています。

Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.

日本語の概要は準備中です。原文の説明を表示しています。

Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.

日本語の概要は準備中です。原文の説明を表示しています。

HuggingFace Transformers with biomedical LMs (BioBERT, PubMedBERT, BioGPT, BioMedLM) for scientific NLP: NER (genes, diseases, chemicals), relation extraction, QA, text classification, abstract summarization. Covers loading, biomedical tokenization, inference pipelines, fine-tuning. Alternatives: spaCy en_core_sci_lg (rule-based NER), Stanza (biomedical models), NLTK.

日本語の概要は準備中です。原文の説明を表示しています。

Use when you need a runnable PyTorch training repo for a medical-imaging task (segmentation, classification, detection, synthesis, self-supervised, or fine-tuning a pretrained backbone). Emits a patient-level seed-locked split, train/evaluate scripts, config and a Methods stub.

日本語の概要は準備中です。原文の説明を表示しています。

Use FlagEmbedding for embedding, reranking, retrieval evaluation, and fine-tuning workflows.

日本語の概要は準備中です。原文の説明を表示しています。

Use Flair for NLP annotation, embeddings, text/sequence model prediction, corpus loading, training/fine-tuning, HunFlair biomedical NER/linking, and production troubleshooting.

日本語の概要は準備中です。原文の説明を表示しています。

Use Donut for OCR-free document understanding, checkpoint inference, fine-tuning, evaluation, and SynthDoG synthetic document generation.

日本語の概要は準備中です。原文の説明を表示しています。

Route Chinese-LLaMA-Alpaca model reconstruction, inference/deployment, training/fine-tuning, and evaluation workflows.

日本語の概要は準備中です。原文の説明を表示しています。

Guides ChatGLM2-6B Transformers inference, local demos, FastAPI/OpenAI-compatible serving, C-Eval evaluation, and P-Tuning v2 fine-tuning.

日本語の概要は準備中です。原文の説明を表示しています。

Use Chronos Forecasting for pretrained time-series forecasting, Chronos-2 covariates, data validation, fine-tuning, evaluation, and deployment planning.

日本語の概要は準備中です。原文の説明を表示しています。

Route Baichuan2 chat inference, deployment/quantization, and fine-tuning workflows.

日本語の概要は準備中です。原文の説明を表示しています。

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

日本語の概要は準備中です。原文の説明を表示しています。

Use AgileRL for reinforcement learning workflows: classical RL training, evolutionary HPO, evolvable networks, multi-agent PettingZoo training, offline/bandit data, and LLM fine-tuning.

日本語の概要は準備中です。原文の説明を表示しています。

Select, integrate, and operate multi-model video-generation gateways — hosted inference aggregators such as fal.ai, Replicate, and WaveSpeed that expose many third-party video (and video-adjacent audio) models behind one account, one API surface, and one bill. Use when deciding whether to route video generation through a gateway versus a direct model-provider API; when comparing gateways on catalog, async/queue job design, webhooks, pricing, schema discovery, and version pinning; and when operating gateway workloads in production — spend controls, retries, cross-gateway failover, content- safety differences, data retention, and commercial-rights passthrough of the underlying model. Not for direct model-provider APIs, local/self-hosted inference, model training/fine-tuning, or image-only gateway use.

日本語の概要は準備中です。原文の説明を表示しています。