unsloth-orpo
One-step preference alignment using Odds Ratio Preference Optimization (ORPO) (triggers: ORPO, preference optimization, alignment, ORPOTrainer, log_odds_ratio, binary preference).
发现 blockchain computational chemistry 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
One-step preference alignment using Odds Ratio Preference Optimization (ORPO) (triggers: ORPO, preference optimization, alignment, ORPOTrainer, log_odds_ratio, binary preference).
Conducts rigorous academic research and document analysis using Gemini's advanced control features (Logprobs, Citations, Long Context).
Fan Selection & Airflow Analysis Agent
Psychrometric Analysis Agent
Coil Selection & Thermal Design Agent
Research product compositions using AI and web sources. Use when needing to find what products, substances, or objects are made of - including ingredients, materials, chemicals, and elements. Essential for buil...
Provides specialized knowledge and content creation for Physical AI and Humanoid Robotics topics with focus on accuracy and peer-reviewed sources.
Analyze completed experiments and craft executive-ready summaries with insights and recommendations.
Use when performing mathematical physics computations - Lie algebras, quantum chemistry, neural operators, theorem proving, or scientific validation. Provides guidance on Theory2 CLI usage, computational workfl...
This skill should be used when conducting bioinformatics research, planning experiments, running analyses, or managing scientific projects. Triggers include requests like "研究を始める", "実験する", "新しい実験...
Assistente para elaboração do PCA de Camocim (Lei 14.133).
CellChat cell-cell communication analysis toolkit - complete documentation with precise file name-based categorization
Comprehensive skill for scvi-tools - Deep probabilistic models for single-cell omics analysis. Use for scVI, scANVI, totalVI, MultiVI models, single-cell RNA-seq integration, batch correction, differential expr...
Comprehensive skill for CellPhoneDB - Database of cell type markers and cell-cell communication analysis for single-cell data. Use for cell type annotation, ligand-receptor analysis, cell-cell interaction infer...
SpatialData framework for handling spatial multi-modal and multi-scale data. Use this skill for questions about spatial omics data analysis, visualization, and the SpatialData Python ecosystem.
Comprehensive skill for scARCHES - Deep learning library for single-cell analysis of chromatin accessibility data. Use for scATAC-seq data processing, model training, batch correction, integration with scRNA-se...
Deep technical assistant for projects that combine Neural Quantum States (FFNN and Transformer-based) with Sample-based Quantum Diagonalization (SQD). Trigger this skill whenever the task involves: (1) designin...
Research documentation and evidence synthesis framework for MYCURE healthcare products using HIGH/MEDIUM/LOW confidence grading, triangulation methodology, and rigorous citation standards. Auto-activates for re...
Expert guidance on statistical analysis methodologies and Monte Carlo simulation for fantasy football. Use this skill when selecting regression approaches, designing simulations, performing variance analysis, o...
Drive quantitative analysis, factor diagnostics, and reporting for ATFT-GAT-FAN outputs.
Expert assistance with GraphPad Prism scientific graphing and statistics software, specializing in Prism scripting for automation, batch processing, and data analysis workflows.
Parse LA-Bench format JSONL files to extract experimental protocol data by ID. This skill should be used when working with LA-Bench datasets to retrieve structured experimental instructions, materials, protocol...
Orchestrate the complete LA-Bench experimental procedure generation workflow from JSONL input to validated output. This skill should be used when processing LA-Bench format experimental data to generate and val...
Validate generated experimental procedures against LA-Bench evaluation criteria. This skill orchestrates formal validation (via script) and semantic evaluation (via subagent) to ensure compliance with LA-Bench...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。