Results for “tvl”

Fetches real-time London transit data from the TfL API, including Tube and bus arrivals, line status, disruptions, journey planning, and route information.

Merlin Chain: largest Bitcoin L2 by TVL (2026), ZK rollup with EVM, 150+ dApps. Federation peg with planned trust-minimization. USE WHEN: evaluating Merlin for deployment, BTC DeFi.

Search movies and TV shows, retrieve cast, ratings, streaming availability, and personalized recommendations via the TMDb API.

Search the web with LLM-optimized results via the Tavily CLI, returning relevant snippets, relevance scores, and metadata. Supports domain filtering, time ranges, and multiple search depths.

VILA: On Pre-training for Visual Language Models

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.

Persistent task ledger for agent coordination. Plan multi-step work, checkpoint progress across session boundaries, and coordinate across multiple agents with project pool routing.

Tracks multi-step work across sessions using the hzl CLI, coordinating sub-agents with checkpoints and leases.

Train LLMs with reinforcement learning using verl (Volcano Engine RL), supporting RLHF, GRPO, PPO, and other algorithms for scalable post-training with flexible infrastructure backends.

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.

Extracts clean markdown or text from one or more URLs using the Tavily CLI, with support for JavaScript-rendered pages and query-focused chunking.

Deploy a Velociraptor server and agents, then write and execute VQL hunts across a fleet of endpoints for threat hunting and incident response.

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.

Crawls websites and saves content from multiple pages as local markdown files using the Tavily CLI, with options for depth, breadth, path filtering, and semantic focus.

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.

Tracks multi-step work across sessions using the hzl CLI, coordinating sub-agents with projects, tasks, checkpoints, and leases.

Search and discover movies, TV shows, and trending content via The Movie Database (TMDb) API v3. Use when the user asks about movies, TV, film, cinema, genres, certifications, ratings, cast, upcoming releases, or trending media.

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

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.

Deploy and operate the RTVI-CV-3D microservice for multi-camera 3D detection and tracking, supporting sample datasets, custom videos, and RTSP streams.

Reduce per-token latency on Jetson vLLM servers by appending speculative decoding configuration, with guidance on when to enable and how to benchmark the improvement.

Trains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.

Performs web search, content extraction, site crawling, URL discovery, and deep research via the Tavily CLI, returning JSON for LLM consumption.

Downloads videos and music from YouTube, Bilibili, X, and other sites into organized local folders, with optional Telegram delivery.

CogVLM: Visual Expert for Pretrained Language Models

Discovers and lists all URLs on a website without extracting content, using the Tavily CLI. Faster than crawling, with options for depth, filtering, and natural language instructions.

Downloads videos and music from YouTube, Bilibili, X, and other sites into organized local folders, with optional playlist subdirectories and Telegram delivery.

Visual Instruction Tuning

Downloads videos and music from URLs using yt-dlp, saving them to standard media folders.

Configure SSL/TLS inspection on network security devices to decrypt, inspect, and re-encrypt HTTPS traffic for threat detection while managing certificates, exemptions, and privacy compliance.

Download Video/Music from YouTube/Bilibili/X/etc.

Toggle the statusline quota pace indicator (mode/theme)

Computes the InfoLM metric from torchmetrics for evaluating text generation against ground truth, with configurable information measures and sentence-level scoring.