Results for “tuning”

Improve PostgreSQL performance through a staged workflow covering slow query analysis, indexes that speed up data access, query rewrites, configuration tuning, routine maintenance, and monitoring for production databases.

• Investigating slow PostgreSQL queries
• Reviewing database indexes
• Tuning database configuration

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.

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

Reduce the memory needed to run large language models with GPTQ quantization, which stores model weights at lower precision. Covers loading compressed models, quantizing your own models, choosing execution backends, and connecting to memory-efficient fine-tuning.

• Run a language model within limited GPU memory
• Load a pre-quantized model for text generation
• Quantize and save your own trained model

Helps adapt LLMs to specific tasks with LLaMA-Factory, including training through a web interface and memory-saving methods such as QLoRA. Provides documentation references for learning features, implementing workflows, and investigating code problems.

• Exploring LLM fine-tuning through a web interface
• Checking LoRA and QLoRA training options
• Investigating LLaMA-Factory implementation problems

Support startup AI strategy by comparing API use, fine-tuning—additional training of an existing model—and in-house development. Assess three-year costs, regulatory risk, self-hosting breakeven points, and hiring priorities to inform leadership decisions.

• Compare API use, fine-tuning, and in-house development
• Assess regulatory risks for an AI use case
• Calculate when self-hosting becomes cost-effective

Get documentation-based help with PostgreSQL queries, database design, administration, and performance tuning. The supplied reference also explains connection settings and libpq, PostgreSQL’s C client library, for investigating connection failures and implementing connection handling.

• Writing SQL and planning database structures
• Checking connection strings and parameter settings
• Investigating connection failures with libpq

Run model training, fine-tuning, inference, and batch jobs on Modal’s cloud GPUs. Estimate hardware needs and cost, generate Python launch scripts, run or deploy workloads, monitor logs, and retrieve results without managing remote servers.

• Test CUDA code without a local GPU
• Run model training or LoRA fine-tuning on cloud GPUs
• Deploy a model inference API or vLLM service

Guides fine-tuning and evaluation of OpenVLA-OFT robot models that turn images and language into actions. Covers LIBERO simulation, ALOHA deployment, LoRA adaptation that updates a small set of parameters, and troubleshooting action scaling or configuration mismatches.

• Evaluate pretrained models in LIBERO
• Fine-tune robot action models with LoRA
• Deploy server-client inference for ALOHA

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.

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

Get guidance on adapting LLMs through additional training with LLaMA-Factory. The skill covers a visual interface requiring no code, LoRA and QLoRA training methods, and documentation-based help with implementation, features, and debugging.

• Learning additional training through a visual interface
• Exploring LoRA and QLoRA training methods
• Checking supported models and multimodal features

Build chat, image generation, and speech transcription features on 0G Compute Network, a distributed GPU marketplace. This skill guides SDK integration, model fine-tuning, response processing for billing, and account funding through code patterns and CLI commands.

• Integrating chat and image generation into an application
• Preparing model fine-tuning jobs
• Checking balances and funding provider accounts

Route NVSHMEM tuning to data collection, remote transport, NIC-to-PE mapping, or TMA. Do not use for unrelated CUDA, NCCL, or application tuning.

The English summary is being prepared. Showing the original description.

Viking Search tuning for specified policy directions. Use this when the user provides specific queries, a type of query, or a business policy direction, and asks to boost, suppress, or fix a class of search results through request-parameter passthrough. You must only perform read-only baseline evaluation and request-level candidate testing; do not modify search scenes, app config, dictionaries, recommend scenes, or primary recall parameters.

The English summary is being prepared. Showing the original description.

Use when the user provides 1-50 concrete bad-case search queries for one Viking Search app and wants local deterministic fixes. This skill only verifies request-level fine-operation interventions against a read-only baseline scene and delivers a console-ready configuration sheet, validated payloads, and a replay script. It must not mutate scenes, apps, dictionaries, datasets, recall core parameters, or online defaults.

The English summary is being prepared. Showing the original description.

Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.

The English summary is being prepared. Showing the original description.

Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training with DeepSpeed or FSDP. Covers dataset prep, training runs, and model export.

The English summary is being prepared. Showing the original description.

Plan, implement, or review vector index tuning work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests vector index tuning work.

The English summary is being prepared. Showing the original description.

Use when adapting large language models to specific tasks, domains, or behaviors - covers LoRA, QLoRA, PEFT, instruction tuning, and full fine-tuning strategiesUse when ", " mentioned.

The English summary is being prepared. Showing the original description.

Expert guide for synthetic dataset generation, LLM-as-a-judge filtering, QLoRA fine-tuning (Unsloth), DPO alignment, and GGUF/Ollama export for local SLMs / Panduan ahli generasi data sintetis, fine-tuning QLoRA, DPO, dan ekspor GGUF/Ollama.

The English summary is being prepared. Showing the original description.

对 DiT（扩散/多模态生成）模型执行 W8A8 动态（data-free）或 W8A8 MXFP8（data-free）量化。覆盖 HunyuanVideo、Wan2.2-T2V/I2V/TI2V、FLUX.1-dev（已迁移）、SD3、Sana、HunyuanDiT、CogViewX 等。YAML apiversion 固定 multimodal_sd_modelslim_v1，统一 MultimodalPipelineInterface 重构路径（不再保留 LegacyMultimodalPipelineInterface）。模板与字段以 msmodelslim/model/hunyuan_video/model_adapter.py（唯一已迁移到重构路径且 lab_practice YAML 已 validated 的 DiT）为参考；其它 DiT 需按各自推理仓的 `parse_args` 调整字段集合。data-free 指不引入外部激活校准数据，spec.dataset（校准集短名，短名如 wan2_2_t2v；enable_dump: false 时不参与 dump）仍必填；精度调优通过下游经验库 L2 §7 + 直接调 `quantization-expert-experience-tuning-rules/scripts/apply_rollback.py`（整层回退）扩展 exclude 列表，闭环由 `quantization-accuracy-tuning-orchestrator` 调度。

The English summary is being prepared. Showing the original description.

在 W8A8 动态量化后，用 MindIE-SD 冒烟测试 DiT 量化权重是否可加载（可选 skill）。与 `quant-tuning-evaluate`（DiT 扩展节）的区别：本 skill 仅做"能跑通 + 权重可用"的轻量验证（4~16 条 prompt，几分钟出结果），不算分；后者产出视频集交 `quant-tuning-score-dit`（AISBench-VBench 16 维度）评分，是调优回路一环。不引入 vLLM-Ascend、不做精度指标评估（FID/CLIP-score 等）。

The English summary is being prepared. Showing the original description.

End-to-end automated model quantization and accuracy tuning workflow. Use when user asks for automated model quantization and accuracy tuning, e.g. "自动量化", "量化调优", "一键量化", "精度调优", etc. 当用户给出多卡（≥2 卡）卡号时，量化阶段通过 EP 并行适配（msmodelslim-ep-parallel-adaptation）保证多卡 EP 并行，调优主流程仍在本 Skill。

The English summary is being prepared. Showing the original description.

Append a DiT-tuning round to history.yaml. DiT-side counterpart of the LLM-path accuracy_append.py; records practice.md5, inference_outputs, fp_baseline_outputs, and the scoring fields (scores / overall_score / loss_vs_baseline / is_satisfied) populated by quant-tuning-score-dit. Idempotent on practice_id.

The English summary is being prepared. Showing the original description.

Plan AI fine-tuning projects with data preparation, training, and evaluation. TRIGGERS - Use when user needs help with ai-fine-tuning-plan related tasks.

The English summary is being prepared. Showing the original description.