Results for “tron”

Adopts the perspective and thinking framework of Justin Sun, using his mental models, decision heuristics, and communication style to analyze crypto industry topics and business decisions.

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning) with support for SFT, DPO, GRPO, KTO, RLOO, and reward model training via CLI commands.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.

Scans TON (The Open Network) smart contracts for 3 critical vulnerabilities including integer-as-boolean misuse, fake Jetton contracts, and forward TON without gas checks. Use when auditing FunC contracts.

Discover trending, anticipated, and popular movies and TV shows via the Trakt.tv API from the terminal. No authentication required for read-only discovery. Use when the user asks about what to watch, trending movies, popular shows, or media discovery.

Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

靖王（古装权谋虚构）认知与表达框架（压缩蒸馏）：耿直宗室、信任成本、笨办法正义 触发：琅琊榜 等。虚构

Manage Trello boards, lists, and cards via the Trello REST API.

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

Implements scheduled cron triggers in Cloudflare Workers, covering handler signatures, multiple schedules, background tasks, workflow integration, and testing.

Manage Trello boards, lists, and cards via the Trello REST API.

Manage Trello boards, lists, and cards via the Trello REST API.

Electron framework for building cross-platform desktop applications with JavaScript, HTML, and CSS. Covers architecture, IPC, security, packaging, auto-updates, and backend integration patterns. USE WHEN: user mentions "Electron", "desktop app", "cross-platform application", asks about "IPC", "main process", "renderer process", "Electron packaging", "auto-updates", "code signing", "Electron security" DO NOT USE FOR: Tauri applications - use `tauri` skill instead

Manage Trello boards, lists, and cards via the Trello REST API.

Manage Trello boards, lists, and cards via the Trello REST API.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Comprehensive guide to trpo. Master the concepts, implementation, best practices, and real-world applications of trpo in professional environments.

Manage Trello boards, lists, and cards via the Trello REST API.

Wire ETL, ingestion, cron, edge-function, and queue jobs correctly. Use for "build a pipeline", "sync X into Y", "nightly aggregation", "cron double-counts", "dedupe", "backfill", "the numbers are wrong after a retry". Bakes in idempotency, atomic writes, data contracts, dead-letter, and observability.

Train reinforcement learning models using torchforge, Meta's PyTorch-native RL library for scalable, algorithm-focused experimentation with GRPO, DAPO, and custom loss functions.

Manage Trello boards, lists, and cards via the Trello REST API.

Implements scheduled handlers for Cloudflare Workers, covering cron triggers, retry control, multiple schedules, workflow integration, and testing.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

Detects and eliminates AI writing tropes that make text sound artificial or formulaic. Use when generating text content, writing documentation, creating code comments, or reviewing writing style. Supports four-tier JSON preferences (global/project x shared/local office.json) read via load-preferences.sh.

Manage Trello boards, lists, and cards via the Trello REST API.

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data, covering correlation testing, available recipes, and multi-GPU examples.

Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI.

Reduces peak GPU memory in Megatron Bridge training by applying expandable segments, parallelism resizing, activation recompute, and CPU offloading constraints.

Enables Megatron Fully Sharded Data Parallel in Megatron-Bridge with configuration overrides, code anchors, pitfalls, and verification steps.

Keeps long AI sessions on track by tracking decisions, detecting scope creep, and flagging drift before it costs work.

Move issues and external pull requests through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

Ranks weekly token unlocks by Absorption Ratio (unlock value / 7d avg volume) instead of supply percentage, with per-event cliff vs linear classification, recipient category, and a one-line market read.

Track code changes with structured JSON records, an enforced state machine, and a session handoff format for AI continuity.