Orchestra Research

Implement Mamba, a model architecture that processes sequences through an internal state with computation scaling linearly with input length. Covers pretrained text generation, Mamba-1 and Mamba-2 configuration, speed comparisons with Transformers, and GPU memory troubleshooting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explore models for long sequences or streaming applications
• Generate text with pretrained Mamba models
• Compare Mamba-1 and Mamba-2 configurations

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Fine-tune language models with TRL using GRPO, a method that compares scored responses to the same prompt. Covers training data, scoring functions, GPU-conscious settings, and monitoring for tasks with measurable correctness or required output formats.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train models to follow JSON or XML output formats
• Reward correct answers in math or coding tasks
• Balance correctness, format, and style during training

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Guide large language model training with OpenRLHF using human preference feedback. Covers training method selection, distributed GPU setup, reward model training, and memory tuning, with examples for PPO, GRPO, and DPO.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a training method for human preference alignment
• Setting up distributed training across multiple GPUs
• Training a reward model before PPO

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Set up reinforcement learning, training guided by rewards, for language models with slime. The skill covers Megatron-LM training, SGLang response generation, data preparation, asynchronous execution, and custom workflows for agents that use tools across multiple turns.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare GRPO training for GLM or Qwen3 models
• Overlap response generation and model training
• Train agents with multi-turn tool use

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Helps fine-tune large language models with LoRA and QLoRA, methods that train small sets of additional parameters. Covers memory-conscious training, configuration choices, saving adapters, and switching task-specific adapters on a shared base model.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fine-tune a model with limited GPU memory
• Choose LoRA settings for a specific task
• Switch task-specific adapters on one base model

Get guidance on adapting LLMs through additional training with LLaMA-Factory. The skill covers a visual interface requiring no code, LoRA and QLoRA training methods, and documentation-based help with implementation, features, and debugging.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learning additional training through a visual interface
• Exploring LoRA and QLoRA training methods
• Checking supported models and multimodal features

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Implement and troubleshoot large-model training with DeepSpeed across multiple GPUs. The skill covers memory optimization, parallel training, and numerical precision choices, alongside examples for storage transfers and models that divide work among specialized components.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review settings for distributed model training
• Tune transfers between NVMe storage and tensors
• Configure training with specialized model components

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• 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

Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspecting attention patterns and intermediate values
• Testing output changes by replacing internal activations
• Analyzing attention head contributions to predictions