Menü
SkillsMP hat 14 Skills aus modelscope/AgentJet gesammelt. Öffne einen Skill, um Quelle und Details zu prüfen.
Es werden 14 von 14 gesammelten Skills angezeigt.
Execute AgentJet reinforcement learning experiments using experiment blueprints in classic (non-swarm) mode. Handles full lifecycle: launch experiment in tmux, monitor progress, analyze errors, collect results, and write finish flag. Use when the user wants…
Quellsprache: Chinesisch
Execute AgentJet reinforcement learning experiments using experiment blueprints in swarm mode. Handles full lifecycle: generate blueprint if needed, launch experiment in tmux, monitor progress, analyze errors, collect results, and write finish flag. Use when…
Quellsprache: Mehrsprachig
Install AgentJet swarm server using Conda. Handles Python 3.10 environment creation, dependency installation with the verl training backbone, flash-attn compilation, and optional PyPI mirror for China users.
Quellsprache: Englisch
Install and run the AgentJet Swarm Server in a Docker container with NVIDIA GPU support. Use when the user wants to deploy a swarm server on a GPU machine via Docker, including GPU driver setup, Docker mirror configuration, model weight mounting, and server…
Quellsprache: Englisch
Download per-step time-series metric data (reward, entropy, response length, etc.) from a SwanLab cloud run URL as a pandas.DataFrame. Use when the user provides a SwanLab URL and wants to fetch or analyze training curves.
Quellsprache: Englisch
Install AgentJet client for connecting to a swarm server. Use when the user only needs to run the AgentJet client (not a swarm server) and does not need to run models locally, e.g. on a laptop. Installs basic requirements via `pip install -e .`.
Quellsprache: Englisch
Map VERL training configuration to AgentJet configuration. Find VERL config in verl_default.yaml, check for existing mappings in config_auto_convertion_verl.jsonc, add new mappings to ajet_default.yaml and the conversion schema, and optionally add parameters…
Quellsprache: Englisch
Convert skills in non-standard formats to the standard Agent Skills `SKILL.md` format. Validates YAML frontmatter (name, description, license, compatibility, metadata, allowed-tools), directory structure (SKILL.md, scripts/, references/, assets/), and best…
Quellsprache: Englisch
Train complex blackbox agents (agents without clear reward signals) using AgentJet. Write dataset collectors, episode runners with LLM-as-Judge reward functions, and integrate with the AgentJet training loop.
Quellsprache: Englisch
Install AgentJet swarm server using the UV package manager. Handles virtual environment creation with Python 3.10, dependency installation with the verl training backbone, flash-attn compilation, and optional PyPI mirror for China users.
Quellsprache: Englisch
Create an active, dataset-driven AgentJet swarm client. Write agent_roll.py and agent_run.py that iterate through a dataset, execute agent workflows, and compute rewards for reinforcement learning training with AgentJet Swarm.
Quellsprache: Englisch
How `max_env_worker` caps the "Running Episodes" gauge, and how `AgentJetJob` relates to the YAML config.
Quellsprache: Englisch
Monitor training progress by reading tmux content with exponential backoff intervals (30s, 1min, 2min, 4min, 8min, 16min), analyze logs when anomalies occur, and provide fix suggestions
Quellsprache: Englisch
Create a passive swarm client that waits for user input instead of iterating through a dataset by itself.
Quellsprache: Englisch