Results for “rl”

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

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 LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

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 LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

Provides storage and environment conventions for NeMo-RL agents on Brev instances, ensuring large experiment outputs go to /ephemeral and secrets are loaded from .env.

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.

Executes Python code iteratively via an MCP bridge to produce verified results for calculations, data analysis, and task decomposition.

Executes Python code iteratively via an MCP bridge to produce verified results for calculations, data analysis, and task decomposition.

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.

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.

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.

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

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

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.

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.

Security controls for RAG. Indirect prompt-injection via retrieved documents, PII detection/redaction (Microsoft Presidio, AWS Comprehend), multi-tenant isolation, ACL-aware retrieval with row-level/metadata filtering, data-leakage prevention, jailbreak hardening on retrieved context, GDPR right-to-be-forgotten in vector DBs. USE WHEN: user mentions "prompt injection RAG", "indirect prompt injection", "PII redaction", "Presidio", "ACL RAG", "row-level security", "multi-tenant RAG isolation", "GDPR vector DB", "right to be forgotten", "jailbreak", "data leakage RAG" DO NOT USE FOR: hallucination detection - use `rag-guardrails`; tenancy scaling patterns - use `rag-production`; audit tracing schema - use `rag-observability`

Universal Reasoning Framework implementing λο.τ calculus over holarchic structures. Provides severity-based routing (R0-R3 pipelines), modular cognitive architecture (DEC, EVL, PAT, SYN, MEA, HYP, INT), fractal execution patterns, multi-level validation (η≥4, KROG), and adaptive learning. Triggers on: (1) complex multi-step reasoning, (2) high-stakes decisions requiring validation, (3) research synthesis across domains, (4) system design and architecture, (5) crisis management, (6) performance optimization. Implements scale-invariant reasoning from micro (tool calls) through meso (skill composition) to macro (orchestrated workflows).

Debug local web or Electron apps interactively using a persistent Playwright session with js_repl, enabling fast iterative UI debugging and visual QA.

Migrate Enzyme tests to React Testing Library for React 18 upgrades with a complete API mapping and behavior-testing philosophy.

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.

Train, evaluate, export, and run inference on TAO action-recognition models for classifying temporal actions in video clips using RGB, optical flow, or joint input.