Results for “large models”

Predict B-cell and T-cell epitopes for vaccine antigen design and epitope mapping with BepiPred-3.0, DiscoTope-3.0, the IEDB tools, and EL-mode MHC presentation. Encodes the load-bearing asymmetry that T-cell epitope prediction is mature (it reduces to MHC presentation, AUC>0.9) while B-cell prediction is unreliable (linear predictors ~AUC 0.6 because ~90% of real epitopes are conformational) — so structure-based DiscoTope-3.0 on AlphaFold models is the only defensible B-cell path, propensity scales are obsolete, and NetChop is largely redundant on EL-trained models. Use when mapping epitopes or selecting vaccine antigens. MHC binding lives in mhc-binding-prediction.

The English summary is being prepared. Showing the original description.

Predict B-cell and T-cell epitopes for vaccine antigen design and epitope mapping with BepiPred-3.0, DiscoTope-3.0, the IEDB tools, and EL-mode MHC presentation. Encodes the load-bearing asymmetry that T-cell epitope prediction is mature (it reduces to MHC presentation, AUC>0.9) while B-cell prediction is unreliable (linear predictors ~AUC 0.6 because ~90% of real epitopes are conformational) — so structure-based DiscoTope-3.0 on AlphaFold models is the only defensible B-cell path, propensity scales are obsolete, and NetChop is largely redundant on EL-trained models. Use when mapping epitopes or selecting vaccine antigens. MHC binding lives in mhc-binding-prediction.

The English summary is being prepared. Showing the original description.

Transcribe audio files locally with Whisper CLI, a command-line tool that needs no API key. Produce text or translated subtitles, and choose smaller or larger models to balance processing speed and accuracy.

• Transcribing recorded audio into text
• Creating translated subtitles from audio
• Choosing a model for speed or accuracy

Get guidance for fine-tuning large language models with Axolotl, adapting them through additional training. Use YAML configuration examples, dataset references, and training methods such as LoRA to set up training and investigate problems.

• Preparing YAML configuration for model fine-tuning
• Exploring LoRA and QLoRA training methods
• Checking dataset formats and API usage

Set up reinforcement learning, training guided by response rewards, for large language models. Use Megatron-LM and SGLang to prepare data, configure training and response generation, and build asynchronous or multi-turn experiments.

• Setting up GRPO training for a language model
• Overlapping response generation and training
• Training agents that use tools across multiple turns

Run machine learning training and predictions on cloud GPUs, then publish models as APIs that other applications can call. The skill guides Python-based setup, automatic scaling, persistent storage, parallel processing, and scheduled jobs.

• Run machine learning jobs without managing GPU servers
• Publish a model as an automatically scaling API
• Process large batches of data in parallel

Set up reinforcement learning, which trains models using rewards, with verl. Follow workflows for preparing data, configuring GRPO or PPO training, scaling across GPUs, and addressing memory errors or unstable training.

• Training a math reasoning model with GRPO
• Configuring PPO training with a critic model
• Scaling large model training across multiple nodes

Configure large language model pretraining with torchtitan across multiple GPUs. Covers ways to split training work, launch jobs on computing clusters, enable Float8 numerical processing, and save or resume training through distributed checkpoints.

• Pretraining Llama 3.1 8B on eight GPUs
• Configuring multi-node training with SLURM
• Enabling Float8 training on H100 GPUs

Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.

• Running GPU inference without managing servers
• Deploying a model as an automatically scaling API
• Processing large batches in parallel

Guide substantial Swift changes in cmux with rules for package boundaries, dependency direction, state management, concurrency, and API documentation. Structure code so public package types can be tested without launching the app.

• Extracting a large app feature into Swift Packages
• Reviewing dependencies between UI, domain models, and services
• Restructuring state management and Swift 6 concurrency

Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.

• Training a language model on example responses
• Training with preferred and rejected response pairs
• Debugging GRPO reward functions and batch settings

Plan projects that use large language models, from checking whether the task suits a model to designing processing stages. Estimate costs, choose single or multiple agents, and organize prototypes, structured outputs, and iteration.

• Checking whether a task is suitable for an LLM
• Designing a pipeline for batch analysis
• Estimating processing costs before development

Build image conversations with LLaVA, a model that connects image recognition with language. This skill guides setup, image descriptions, visual questions, and follow-up conversations, with examples for Python, command-line use, and a Gradio interface.

• Build a chatbot that answers questions about images
• Write detailed descriptions of photos
• Ask follow-up questions about the same image

Configure large language model pretraining with torchtitan across multiple GPUs. Covers ways to split training work, launch jobs on computing clusters, enable Float8 numerical processing, and save or resume training through distributed checkpoints.

• Pretraining Llama 3.1 8B on eight GPUs
• Configuring multi-node training with SLURM
• Enabling Float8 training on H100 GPUs

Guides you through running large language models on CPUs, Apple Silicon, and AMD or Intel GPUs. Covers choosing GGUF model files, reducing memory through quantization, and starting an OpenAI-compatible chat server.

• Running a local LLM on an Apple Silicon Mac
• Trying LLM inference on a CPU-only machine
• Choosing a model format that fits available memory

Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.

• Running GPU inference without managing servers
• Deploying a model as an automatically scaling API
• Processing large batches in parallel

Guides LLM training with verl using rewards to improve model responses. Covers data preparation, reward functions, GRPO and PPO configuration, distributed GPU training, and troubleshooting memory shortages or unstable training.

• Train math reasoning models with GRPO and answer-based rewards
• Configure PPO training with a separate value-estimation model
• Run large-model training across multiple GPU nodes

Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.

• Training a language model on example responses
• Training with preferred and rejected response pairs
• Debugging GRPO reward functions and batch settings

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.

The English summary is being prepared. Showing the original description.

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

The English summary is being prepared. Showing the original description.

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).

The English summary is being prepared. Showing the original description.

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).

The English summary is being prepared. Showing the original description.

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

The English summary is being prepared. Showing the original description.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

The English summary is being prepared. Showing the original description.