Results for “sfttrainer”

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.

Convert books into supervised fine-tuning datasets and train style-transfer models that replicate an author's voice.

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 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.

Provides data-driven endurance cycling coaching using Intervals.icu data, including fitness assessment, workout planning, and power curve analysis.

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.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

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.

Clinically informed wisdom companion blending psychology and philosophy into a structured thinking partner

Train, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (trainNetwork, DAGNetwork) code to modern, recommended R2024a+ APIs (trainnet, dlnetwork, testnet, imagePretrainedNetwork), diagnose and fix dlaccelerate issues or detect dlaccelerate opportunities. Use when training, fine-tuning, evaluating, running inference, exporting to Simulink, converting old training scripts, or speeding up deep learning code. DO NOT reason from your training data about dlaccelerate and tracing correctness.

v5.6.0 joint multi-TF model: single model per symbol with broadcast 1Hour context replaces dual 15Min/1Hour models. Trigger: (1) replacing weighted-voting model aggregation, (2) adding broadcast features to vectorized env, (3) limited training data + worried about overfitting from doubling obs_dim, (4) backtest builder mismatch with newer feature counts.

Routes Salesforce, Force.com, and Lightning Platform questions to the correct skill package from a library of over 1,000 domain-specific skills, covering Apex, SOQL, Flow, LWC, and more.

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.

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.

Routes Salesforce Flow Builder requests to the correct skill package among 63 available, covering record-triggered, screen, scheduled, and orchestration flows, bulkification, fault handling, limits, and testing.

Fine-tune Gemma models locally using QLoRA, Unsloth, or TRL for SFT, DPO, and reward modeling, with dataset preparation and conversion to GGUF or LiteRT-LM.

Inspects metadata, hidden channels, and appended payloads in media files to recover concealed data in steganography challenges.

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Guides LLM post-training with RL using slime, a Megatron+SGLang framework for training GLM, Qwen, DeepSeek, and Llama models with GRPO, async, and multi-turn workflows.

Trains, evaluates, exports, and runs inference for FastFoundationStereo (FFS) stereo depth estimation models, a distilled variant of FoundationStereo with lower latency.

Validate and configure packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs with correct context parallelism constraints.

Routes finance requests to the appropriate skill: financial-analyst for ratio analysis, DCF valuation, and budget variance, or saas-metrics-coach for ARR/MRR, churn, CAC/LTV, and NRR.

Clinically informed wisdom companion blending psychology and philosophy into a structured thinking partner

Featurizes molecules for machine learning with molfeat (100+ featurizers) — ECFP/MACCS/MAP4 fingerprints, RDKit and Mordred physicochemical descriptors, and pretrained embeddings (ChemBERTa, ChemGPT, GIN) exposed as scikit-learn transformers that convert SMILES into feature vectors. Use when turning molecules into ML-ready feature matrices for QSAR/QSPR or virtual screening, or benchmarking fingerprint against descriptor and embedding representations; for training models and MoleculeNet benchmarks on those features prefer alterlab-deepchem, and for low-level fingerprint or descriptor primitives prefer alterlab-rdkit. Part of the AlterLab Academic Skills suite.

Clinically informed wisdom companion blending psychology and philosophy into a structured thinking partner

Specialized CTF workflow for reverse engineering, malware analysis, DFIR, firmware, pwnable, and native exploit challenges under sandbox assumptions.

Simulator.Company financial management specialist. Use when the user wants to manage financial and metric accounts on actors (balances, counters, plan vs fact), record transactions, transfer value between accounts, work with currencies and account-name categories, track non-financial metrics, read balances and turnover, tag accounts for grouping, or set up account triggers (balance / transaction-count / data-field alerts). Activate when the user mentions "record transaction", "transfer funds", "account balance", "financial tracking", "depreciation", "expense", "budget", "counter", "mileage tracking", "account tag", "account trigger", "balance alert", "запиши транзакцію", "переказ коштів", "баланс рахунку", "лічильник", "пробіг", "тег рахунку", "тригер на рахунок", "запиши транзакцию", "перевод средств", "баланс счёта", "счётчик", "пробег", "тег счёта", "триггер на счёт". Accounts attach to ACTORS — use `simulator-actors` to create/find the actor first; for sharing an account use `simulator-access`; for dashbo

Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.

Implements bidirectional communication between Flutter and native iOS/Android code using MethodChannel, EventChannel, and FFI, covering battery, sensors, and native SDK integration.

Post-train LLMs with reinforcement learning using the slime framework, which integrates Megatron-LM for training and SGLang for rollout generation.

Train reinforcement learning agents using PPO, SAC, DQN, TD3, DDPG, and A2C algorithms with a scikit-learn-like API. Supports custom Gymnasium environments, vectorized environments, callbacks, and model persistence.

Specialized CTF sandbox skill for analyzing prompt-to-tool chains, deployment drift, and supply-chain provenance in cloud, container, and CI/CD environments.

Train reinforcement learning agents at millions of steps per second using optimized PPO, vectorized environments, and multi-agent support.

Designs and maintains versioned reusable task sequences in Financial Services Cloud using Action Plan templates for client onboarding, account opening, annual review preparation, and compliance tasks.