Results for “no retraining”

Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".

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

Configure large language model pretraining with torchtitan across multiple GPUs. Covers ways to split training work, launch jobs on computing clusters, enable Float8 numerical processing, and save or resume training through distributed checkpoints.

• Pretraining Llama 3.1 8B on eight GPUs
• Configuring multi-node training with SLURM
• Enabling Float8 training on H100 GPUs

Configure large language model pretraining with torchtitan across multiple GPUs. Covers ways to split training work, launch jobs on computing clusters, enable Float8 numerical processing, and save or resume training through distributed checkpoints.

• Pretraining Llama 3.1 8B on eight GPUs
• Configuring multi-node training with SLURM
• Enabling Float8 training on H100 GPUs

Set up large language model pretraining with TorchTitan and PyTorch. Configure training across multiple GPUs, combine four ways of splitting the workload, enable Float8 calculations on H100 hardware, and manage checkpoints for saving and resuming training.

• Pretraining Llama 3.1 8B on a single node
• Launching training across multiple nodes with SLURM
• Configuring Float8 training for H100 GPUs

Work with Waypoint models to analyze microbiome samples, the communities of microbes in a sample. Convert taxonomic abundance tables, generate numerical sample representations, configure further training for prediction tasks, and evaluate models on the Compass benchmark.

• Convert microbiome abundance tables into Waypoint inputs
• Generate sample vectors for clustering and visualization
• Configure further training with sample labels

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.

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

Combine capabilities from multiple fine-tuned LLMs without retraining using mergekit. Choose a merging method, configure how models are blended, and evaluate the resulting model on tasks such as math, code generation, and conversation.

• Combining math, coding, and conversation capabilities
• Blending two models at different ratios
• Comparing variants made with different merging methods

Combine specialized language models without retraining using mergekit. The skill explains how to choose merging methods, configure each model’s contribution, compare resulting variants, and prepare a merged model for evaluation and deployment.

• Combine math, coding, and conversation capabilities
• Compare model variants with different merge weights
• Choose a method for merging several models

Analyze and modify refusal behavior in open-weight language models without retraining. Use OBLITERATUS to select methods suited to available hardware, compare approaches, and evaluate changes in refusal rates and response quality.

• Studying how language models produce refusals
• Testing refusal-related weight changes without retraining
• Selecting models and methods for available hardware

Build and troubleshoot TorchDrug 0.2.1 workflows for molecular property prediction, molecule generation, protein modeling, and knowledge graph reasoning. Connect datasets, models, training tasks, and evaluation while checking version compatibility and common implementation errors.

• Training and evaluating molecular property prediction models
• Building molecule generation workflows
• Learning representations of protein sequences and structures

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.

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

Use ML.NET to train, evaluate, or integrate machine-learning models into .NET applications with realistic data preparation, inference, and deployment expectations. USE FOR: ML.NET integration; local model training or retraining; inference pipelines, model loading, evaluation, and deployment review. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.

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

Think and work like an expert Computer Vision Scientist. Use when a task calls for Computer Vision Scientist judgment. Reasons from image formation, projective geometry (pinhole intrinsics and extrinsics, epipolar/PnP/bundle adjustment, similarity-scale ambiguity), and COCO/LVIS AP mechanics through DINOv3/SigLIP 2 foundation baselines, RF-DETR/YOLO26/SAM 3 models, COLMAP 4/GLOMAP and VGGT geometry, pycocotools/TrackEval/BOP evaluation, and CVPR reporting and EU AI Act limits while treating train–test and pretraining leakage, AP evaluation-setting gaming, preprocessing mismatches (EXIF, BGR, aliased resizing), label noise, and camera-convention and scale errors as first-class failure modes.

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

Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver API.

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

Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver API.

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

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

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

Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.

• Studying language model architecture through readable code
• Fine-tuning a model on custom instruction data
• Configuring LoRA training for a single GPU

Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.

• Studying language model architecture through readable code
• Fine-tuning a model on custom instruction data
• Configuring LoRA training for a single GPU

Use when polishing, diagnosing, tailoring, or exporting resumes for LLM, RAG, Agent, Agentic RL, post-training, pretraining, AIGC, search/ranking, multimodal, AI backend, or LLM algorithm internships from raw resume text, a materials folder, and/or a target job description. Audits evidence, maps JD fit, enforces truth boundaries, writes polished and targeted resumes, generates interviewer-style grilling questions, answer cards, evidence-upgrade plans, and optional open-source project recommendations without fabricating experience.

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

Maps query single-cell data to reference atlases using scArches transfer learning with scVI and scANVI models. Transfers cell type labels without retraining on combined data. Use when annotating new single-cell datasets using pre-trained reference models.

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

Builds a GPT and BPE tokenizer from scratch. Use when implementing autograd, attention, a nanoGPT loop, muP hyperparameter transfer, WSD annealing, loss spikes, or mid-training.

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

Somatic movement and whole-body retraining as Joseph Pilates designed it in the Contrology method and as Moshé Feldenkrais designed it in Awareness Through Movement and Functional Integration, with enough cross-reference to the broader somatics landscape (Alexander Technique, Hanna Somatics, Body-Mind Centering) that an agent can place a user into the right method. Covers the Pilates reformer and mat system, the six Pilates principles, the Feldenkrais ATM lesson structure, the nervous-system learning frame that distinguishes somatics from exercise, and the safety posture that matters for rehab populations. Use for queries about core training, rehab-adjacent movement, chronic pain patterns, and learning-based movement re-education.

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

Mescle múltiplos modelos ajustados usando mergekit para combinar capacidades sem retreinar. Use ao criar modelos especializados misturando expertise específica de domínio (math + coding + chat), melhorando performance além de modelos únicos, ou experimentando rapidamente variantes de modelos. Cobre SLERP, TIES-Merging, DARE, Task Arithmetic, mesclagem linear e estratégias de deploy em produção.

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