Orchestra Research

Add PyTorch FSDP2 to training scripts so model state can be split across GPUs. Covers distributed initialization, mixed precision, CPU offloading, and checkpoint saving and loading for models that exceed a single GPU's memory.

中文简介正在准备中。当前显示英语简介。

• Training a model that exceeds one GPU's memory
• Adding FSDP2 to an existing training script
• Configuring mixed precision and CPU offloading

Organize PyTorch training code with LightningModule and Trainer. This skill guides training, validation, logging, model checkpoint saving, early stopping when progress stalls, and configuration for running the same model across multiple GPUs.

中文简介正在准备中。当前显示英语简介。

• Organize existing PyTorch training code
• Add validation and metric logging
• Save the best models and stop stalled training

Helps adapt machine learning training to multiple GPUs and machines with Ray Train. Covers resource allocation, recovery from saved training states, and Ray Tune searches that compare settings such as learning rate and batch size.

中文简介正在准备中。当前显示英语简介。

• Adapt existing PyTorch training to multiple GPUs
• Run HuggingFace training across multiple machines
• Compare learning rates and batch sizes with Ray Tune

Guides setup and operation of Lambda Labs GPU instances for machine learning training and inference. Covers SSH access, persistent storage, API automation, and multi-GPU or multi-node training, including how to retain checkpoints and terminate idle instances.

中文简介正在准备中。当前显示英语简介。

• Setting up a GPU instance for LLM fine-tuning
• Keeping datasets and checkpoints between sessions
• Automating instance launch and termination through the API

Configure machine learning training and batch jobs across multiple clouds with SkyPilot. The skill guides GPU selection, lower-cost cloud and region choices, and automatic recovery when discounted spot instances are interrupted.

中文简介正在准备中。当前显示英语简介。

• Choose a lower-cost cloud for GPU training
• Run long training jobs with recovery after interruptions
• Configure distributed training across multiple machines

Compress large language model weights to four bits with AWQ, a method that uses model activation patterns to limit quality loss. Follow workflows for quantization, loading compressed models, and serving them with vLLM using less GPU memory.

中文简介正在准备中。当前显示英语简介。

• Running large language models with limited GPU memory
• Quantizing a model with domain-specific text
• Serving an AWQ model with vLLM

Helps reduce GPU memory use by loading large language models in 4-bit or 8-bit formats, a technique called quantization. Covers bitsandbytes configuration, memory checks, QLoRA fine-tuning, and training with memory-saving optimizers.

中文简介正在准备中。当前显示英语简介。

• Load a larger model within available GPU memory
• Compare 4-bit and 8-bit quantization settings
• Fine-tune a quantized model with QLoRA

Optimize transformer attention, the calculation that relates tokens to one another, using Flash Attention. The skill guides PyTorch integration, GPU memory reduction, performance measurement, and output comparisons for training or inference with long sequences.

中文简介正在准备中。当前显示英语简介。

• Reducing GPU memory use with long sequences
• Integrating Flash Attention into PyTorch models
• Comparing runtime and outputs before and after changes

Convert language models to GGUF and reduce their size through quantization, which stores model weights at lower precision. Guides cover compression choices, local inference on CPUs and Apple Silicon, and integration with tools such as Ollama.

中文简介正在准备中。当前显示英语简介。

• Running a language model on a CPU-only computer
• Choosing model compression for available memory
• Configuring Metal acceleration on Apple Silicon

Compress large language models to 4-bit weights to reduce GPU memory needs and accelerate text generation. Covers loading compressed models, converting your own models, choosing settings, and preparing memory-efficient fine-tuning with transformers and PEFT.

中文简介正在准备中。当前显示英语简介。

• Run language models with limited GPU memory
• Convert your own model to 4-bit weights
• Compare compression settings for quality and speed

Apply HQQ quantization, which stores language model weights using fewer bits without calibration examples. Covers precision settings, inference backends, saving compressed models, deployment with HuggingFace Transformers or vLLM, and further training with LoRA.

中文简介正在准备中。当前显示英语简介。

• Compressing a model without calibration data
• Comparing 4-bit and 2-bit quantization settings
• Running quantized models with HuggingFace Transformers or vLLM

Evaluate code generation models with HumanEval, MBPP, and multilingual benchmarks. The skill guides test execution and model comparisons using pass@k, an estimate of whether at least one of k generated solutions passes the tests.

中文简介正在准备中。当前显示英语简介。

• Compare code generation models on shared benchmarks
• Measure code generation performance across languages
• Evaluate instruction-tuned coding models

Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.

中文简介正在准备中。当前显示英语简介。

• Compare models on standard knowledge and reasoning tests
• Track model performance across training checkpoints
• Organize evaluation results for research reports

Evaluate language models on knowledge, math, coding, safety, and image understanding benchmarks. The skill guides reproducible runs in containers using local Docker, Slurm clusters, or cloud execution, with shared configurations for model comparison and result export.

中文简介正在准备中。当前显示英语简介。

• Comparing models on the same benchmark tasks
• Running a small evaluation sample before a full benchmark
• Running large evaluations on a Slurm cluster

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.

中文简介正在准备中。当前显示英语简介。

• 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

Guides PyTorch model training and fine-tuning, from choosing architectures to configuring optimizers and learning rates. Provides troubleshooting steps for unstable loss and memory shortages, plus methods for improving GPU throughput and comparing experiments.

中文简介正在准备中。当前显示英语简介。

• Choose model architectures for the available data type and scale
• Configure optimizers and learning-rate schedules
• Investigate loss spikes, NaNs, and GPU memory shortages

Use Meta's Prompt Guard to detect malicious instructions in user prompts and external data. This skill guides input filtering, batch checks for retrieved documents, detection threshold adjustments, and splitting long text for inspection.

中文简介正在准备中。当前显示英语简介。

• Detecting attempts to override an LLM's instructions
• Checking API responses for embedded malicious instructions
• Batch screening documents retrieved for RAG

Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.

中文简介正在准备中。当前显示英语简介。

• Studying language model architecture through readable code
• Fine-tuning a model on custom instruction data
• Configuring LoRA training for a single GPU

Guides you through setting up RWKV, generating text, processing long documents in chunks, and fine-tuning models. Explains how to carry context between steps and compare memory use with Transformer models.

中文简介正在准备中。当前显示英语简介。

• Build streaming text generation
• Process long documents in chunks
• Plan RWKV fine-tuning

Guides LLM fine-tuning with Axolotl, from YAML configuration and dataset formats to distributed training across GPUs. Covers LoRA and QLoRA, methods that train on preferences, multimodal support, and troubleshooting using documentation references and code examples.

中文简介正在准备中。当前显示英语简介。

• Prepare YAML settings for LLM fine-tuning
• Explore LoRA, QLoRA, and preference training options
• Check dataset formats and input handling

Get guidance on fine-tuning language models with Unsloth, including LoRA and QLoRA methods for training with fewer resources. The skill points to documentation for understanding APIs, implementing training code, debugging problems, and exploring speed and memory optimizations.

中文简介正在准备中。当前显示英语简介。

• Exploring faster training with lower memory use
• Learning about LoRA and QLoRA fine-tuning
• Checking Unsloth features and APIs

Guides experiments that inspect and modify internal values in PyTorch models to study their effects on predictions. Covers local analysis and remote experiments through NDIF for models too large for local GPUs.

中文简介正在准备中。当前显示英语简介。

• Inspect internal values and attention patterns across layers
• Replace internal values to compare changes in predictions
• Run large-model experiments without local GPUs

Explore training workflows that reduce harmful model responses using a written set of principles. The skill covers self-critique, revised training examples, and RLAIF, reinforcement learning from AI feedback, with implementation examples and hardware guidance.

中文简介正在准备中。当前显示英语简介。

• Designing principles for model safety training
• Creating training examples through self-critique and revision
• Planning reinforcement learning with AI-rated responses

Add safety checks to LLM applications with NeMo Guardrails. This skill guides input and output validation, detection of attempts to bypass safety rules, personal information masking, and checks for unsupported or inaccurate answers.

中文简介正在准备中。当前显示英语简介。

• Detect attempts to bypass an AI app's safety rules
• Mask personal information before processing
• Add fact-checking to generated answers