Turn bookmarks into markdown for your agents
Turn X bookmarks, Chrome tabs + YouTube URLs into markdown for agents 🦞 ↗
home / skills / orchestra-research
orchestra-research skills
Find 91 skills from 1 repo created by orchestra-research on GitHub.
Sponsored
ray-data
orchestra-research/ai-research-skills
5.2k
This skill helps you scale ML data processing with Ray Data, enabling streaming, GPU-accelerated transforms, and seamless integration with ML frameworks.
0-autoresearch-skill
orchestra-research/ai-research-skills
5.2k
This skill automates end-to-end AI research projects by managing loops, literature search, experiments, and synthesis to guide direction and produce papers.
bitsandbytes
orchestra-research/ai-research-skills
5.2k
This skill helps you quantize large language models to 8-bit or 4-bit with minimal accuracy loss to reduce memory and speed up inference.
verl
orchestra-research/ai-research-skills
5.2k
This skill guides reinforcement learning based training of large language models using verl across PPO, GRPO, and other RL algorithms.
grpo-rl-training
orchestra-research/ai-research-skills
5.2k
This skill guides GRPO/RL fine-tuning with TRL to enforce formats, optimize reasoning, and align domain-specific behaviors using reward-based training.
pytorch-fsdp2
orchestra-research/ai-research-skills
5.2k
This skill helps you integrate PyTorch FSDP2 into training scripts with correct initialization, sharding, mixed precision, and DTensor-based checkpointing.
weights-and-biases
orchestra-research/ai-research-skills
5.2k
This skill helps you track ML experiments, visualize training, sweep hyperparameters, and manage models using Weights & Biases for streamlined MLOps.
autogpt
orchestra-research/ai-research-skills
5.2k
This skill helps you design, deploy, and monitor autonomous AI agents with a visual builder and persistent execution.
sglang
orchestra-research/ai-research-skills
5.2k
This skill speeds up structured generation and agent workflows with prefix caching for JSON outputs and tool calls, boosting latency and throughput.
accelerate
orchestra-research/ai-research-skills
5.2k
This skill simplifies distributed training with HuggingFace Accelerate, enabling seamless multi-GPU/TPU setups via a four-line integration.
20-ml-paper-writing
orchestra-research/ai-research-skills
5.2k
This skill helps you draft publication-ready ML papers for top conferences by providing proactive drafting, citation verification, LaTeX templates, and
slime
orchestra-research/ai-research-skills
5.2k
This skill helps you accelerate RL-based LLM post-training with slime's Megatron-LM and SGLang for scalable data generation and rollout.
sentence-transformers
orchestra-research/ai-research-skills
5.2k
This skill helps generate high-quality embeddings for semantic search and retrieval using sentence-transformers, enabling efficient RAG, clustering, and
swanlab
orchestra-research/ai-research-skills
5.2k
This skill guides open-source experiment tracking with SwanLab for local or self-hosted ML workflows, including media logging and visual dashboards.
lambda-labs
orchestra-research/ai-research-skills
5.2k
This skill helps you manage Lambda Labs GPU Cloud resources for scalable ML training and inference with persistent storage and easy SSH access.
llava
orchestra-research/ai-research-skills
5.2k
This skill helps you build and use vision-language AI chat capabilities, enabling multi-turn image analysis and VQA with LLaVA.
awq
orchestra-research/ai-research-skills
5.2k
This skill helps you deploy large language models with 4-bit AWQ quantization, delivering 2.5-3x faster inference while preserving accuracy.
cosmos-policy
orchestra-research/ai-research-skills
5.2k
This skill evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulations, enabling efficient setup, headless rendering, and latency profiling for robotics
llamaindex
orchestra-research/ai-research-skills
5.2k
This skill helps you build powerful RAG applications by ingesting documents, indexing data, and querying with LlamaIndex.
langsmith
orchestra-research/ai-research-skills
5.2k
This skill helps you debug, evaluate, and monitor LLM applications with LangSmith observability, capturing traces, datasets, and metrics for reliable AI
axolotl
orchestra-research/ai-research-skills
5.2k
This skill provides expert guidance for fine-tuning LLMs with Axolotl, including YAML configs, 100+ models, and multimodal support.
saelens
orchestra-research/ai-research-skills
5.2k
This skill helps you train and analyze Sparse Autoencoders with SAELens to extract interpretable, monosemantic features from neural activations.
pytorch-lightning
orchestra-research/ai-research-skills
5.2k
This skill helps you streamline PyTorch Lightning training, automate distributed execution, and reduce boilerplate for scalable, reproducible experiments.
llamaguard
orchestra-research/ai-research-skills
5.2k
This skill helps you apply expert content moderation with LlamaGuard to filter unsafe prompts and outputs across chat systems.
qdrant
orchestra-research/ai-research-skills
5.2k
This skill helps you implement high-performance vector similarity search for production RAG systems with fast nearest neighbor and flexible filtering.
audiocraft
orchestra-research/ai-research-skills
5.2k
This skill helps you generate music or sounds from text descriptions using AudioCraft, enabling melody-conditioned and stereo audio output.
nnsight
orchestra-research/ai-research-skills
5.2k
This skill helps you run interpretability experiments on massive PyTorch models remotely using nnsight and optional NDIF, with a single code path.
prompt-guard
orchestra-research/ai-research-skills
5.2k
This skill detects prompt injections and jailbreak attempts in LLM apps, ensuring safer interactions and reliable third-party data filtering.
tensorboard
orchestra-research/ai-research-skills
5.2k
This skill helps you visualize training metrics, debug models, compare experiments, and profile performance with TensorBoard.
pinecone
orchestra-research/ai-research-skills
5.2k
This skill helps you manage production-grade vector search with Pinecone, delivering low-latency, serverless indexing and hybrid search capabilities.
stable-diffusion
orchestra-research/ai-research-skills
5.2k
This skill helps you generate high-quality images from text prompts, perform image-to-image tasks, and optimize diffusion workflows with Stable Diffusion.
brainstorming-research-ideas
orchestra-research/ai-research-skills
5.2k
This skill guides researchers through structured ideation frameworks to uncover high-impact research directions, offering actionable prompts and evaluation
miles
orchestra-research/ai-research-skills
5.2k
This skill guides enterprise RL training with miles for large MoE models, enabling FP8/INT4, train-inference alignment, and speculative RL for throughput.
gptq
orchestra-research/ai-research-skills
5.2k
This skill helps you compress large language models to 4-bit precision with minimal accuracy loss, enabling faster inference and smaller memory footprints.
modal
orchestra-research/ai-research-skills
5.2k
This skill guides you to run ML workloads on Modal's serverless GPU platform with automatic scaling and on-demand pricing.
langchain
orchestra-research/ai-research-skills
5.2k
This skill helps you rapidly build LLM applications using agents, chains, and RAG with multi-provider support and robust tooling.
faiss
orchestra-research/ai-research-skills
5.2k
This skill enables fast billion-scale vector similarity with FAISS, guiding deployment, index selection, and GPU-accelerated search for high-performance
blip-2
orchestra-research/ai-research-skills
5.2k
This skill helps you perform vision-language tasks such as captioning, VQA, and multimodal chat using BLIP-2 with frozen encoders.
clip
orchestra-research/ai-research-skills
5.2k
This skill enables zero-shot image understanding and cross-modal retrieval using CLIP for image search, moderation, and vision-language tasks.
model-pruning
orchestra-research/ai-research-skills
5.2k
This skill helps you compress large language models with pruning techniques like Wanda and SparseGPT, achieving 40-60% size reduction with minimal accuracy
unsloth
orchestra-research/ai-research-skills
5.2k
This skill provides expert guidance for fast fine-tuning with Unsloth, enabling 2-5x training speed and reduced memory usage.
nemo-curator
orchestra-research/ai-research-skills
5.2k
This skill optimizes LLM data curation with GPU-accelerated, multi-modal cleaning, deduplication, and PII redaction to improve training data quality.
flash-attention
orchestra-research/ai-research-skills
5.2k
This skill accelerates transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction on long sequences.
crewai
orchestra-research/ai-research-skills
5.2k
This skill helps you orchestrate teams of autonomous agents for complex tasks with memory, roles, and production-ready workflows.
creative-thinking-for-research
orchestra-research/ai-research-skills
5.2k
This skill helps researchers generate genuinely novel CS and AI ideas by applying cognitive science frameworks like combinatorial creativity and constraint
instructor
orchestra-research/ai-research-skills
5.2k
This skill extracts and validates structured data from LLM responses using Pydantic, with automatic retries and real-time streaming.
skypilot
orchestra-research/ai-research-skills
5.2k
This skill helps orchestrate ML workloads across multiple clouds with automatic cost optimization and spot instance recovery.
constitutional-ai
orchestra-research/ai-research-skills
5.2k
This skill helps you align AI safety using self-critique and AI feedback, reducing harmful outputs without human labeling.
tensorrt-llm
orchestra-research/ai-research-skills
5.2k
This skill optimizes LLM inference on NVIDIA GPUs with TensorRT for maximum throughput and lowest latency in production.
litgpt
orchestra-research/ai-research-skills
5.2k
This skill helps you implement and train LLMs with LitGPT across 20+ pretrained architectures for clean, production-ready workflows.
speculative-decoding
orchestra-research/ai-research-skills
5.2k
This skill accelerates LLM inference using speculative decoding, Medusa heads, and lookahead techniques to boost speed and reduce latency.
nemo-guardrails
orchestra-research/ai-research-skills
5.2k
This skill enforces runtime safety for LLMs with configurable jailbreaking, toxicity, PII, and fact-checking rails to improve reliability.
outlines
orchestra-research/ai-research-skills
5.2k
This skill guarantees valid JSON/XML/code structures during generation using constrained token sampling and Pydantic-backed outputs.
moe-training
orchestra-research/ai-research-skills
5.2k
This skill helps you train large-scale Mixture of Experts models with DeepSpeed or HuggingFace efficiently, reducing compute while expanding capacity.
rwkv
orchestra-research/ai-research-skills
5.2k
This skill helps you optimize sequence processing with RWKV by combining parallel training and sequential inference for long-context models.
sentencepiece
orchestra-research/ai-research-skills
5.2k
This skill helps you implement language-independent tokenization with SentencePiece to support multilingual models and reproducible vocabularies.
vllm
orchestra-research/ai-research-skills
5.2k
This skill helps deploy high-throughput LLM serving with vLLM, enabling OpenAI-compatible endpoints, quantization, and tensor parallelism for production
peft
orchestra-research/ai-research-skills
5.2k
This skill enables memory-efficient fine-tuning of large language models using LoRA, QLoRA, and adapters to save GPU memory.
chroma
orchestra-research/ai-research-skills
5.2k
This skill helps you implement open-source embedding storage and semantic search for AI apps with RAG workflows using Chroma.
dspy
orchestra-research/ai-research-skills
5.2k
This skill helps you build complex AI systems with declarative LM programming, automatic prompt optimization and modular RAG pipelines for reliable outputs.
whisper
orchestra-research/ai-research-skills
5.2k
This skill enables robust multilingual speech-to-text and translation workflows using Whisper across podcasts, meetings, and noisy audio for accurate
transformer-lens
orchestra-research/ai-research-skills
5.2k
This skill helps researchers inspect and patch transformer internals using HookPoints and activation caching to study circuits and attention.
nanogpt
orchestra-research/ai-research-skills
5.2k
This skill helps you learn transformer basics by guiding you through nanoGPT style GPT-2 reproduction, training, and experimentation for educational purposes.
trl-fine-tuning
orchestra-research/ai-research-skills
5.2k
This skill guides fine-tuning LLMs with TRL for instruction tuning, preference alignment, and reward-based optimization, aligning models to human feedback.
llama-factory
orchestra-research/ai-research-skills
5.2k
This skill provides expert guidance for fine-tuning LLaMA models with Llama-Factory, covering APIs, setup, and best practices for multimodal, 8-bit QLoRA
huggingface-tokenizers
orchestra-research/ai-research-skills
5.2k
This skill accelerates tokenization and tokenizer training with HuggingFace Tokenizers, delivering ultra-fast performance and alignment support for NLP
llama-cpp
orchestra-research/ai-research-skills
5.2k
This skill enables efficient LLM inference on CPU and non-NVIDIA hardware, enabling edge deployment and Apple Silicon performance with GGUF quantization.
simpo
orchestra-research/ai-research-skills
5.2k
This skill helps you optimize alignment training with SimPO, delivering faster, reference-free preference optimization for better model alignment.
mamba
orchestra-research/ai-research-skills
5.2k
This skill helps you deploy and experiment with Mamba selective state-space models for efficient linear-time sequence processing on GPUs.
lm-evaluation-harness
orchestra-research/ai-research-skills
5.2k
This skill benchmarks LLMs across 60+ tasks, helping you compare models, track progress, and report standardized academic results efficiently.
model-merging
orchestra-research/ai-research-skills
5.2k
This skill merges multiple fine-tuned models with mergekit to create specialized, higher-performing models without retraining.
openvla-oft
orchestra-research/ai-research-skills
5.2k
This skill fine-tunes and evaluates OpenVLA-OFT policies for robot action generation with LoRA and FiLM conditioning.
openpi
orchestra-research/ai-research-skills
5.2k
This skill helps you fine-tune and deploy OpenPI pi0, pi0-fast, or pi0.5 models for robot policy inference across ALOHA, DROID, LIBERO.
guidance
orchestra-research/ai-research-skills
5.2k
This skill helps you enforce structured generation with regex and grammars, guaranteeing valid JSON/XML/code and guiding multi-step workflows.
megatron-core
orchestra-research/ai-research-skills
5.2k
This skill helps you optimize large-scale LLM training with Megatron-Core, enabling efficient 2B-462B parameter models using advanced parallelism.
openrlhf
orchestra-research/ai-research-skills
5.2k
This skill speeds high-performance RLHF training for large models with Ray and vLLM acceleration, simplifying distributed PPO GRPO DPO workflows
ray-train
orchestra-research/ai-research-skills
5.2k
This skill orchestrates distributed training with Ray Train to scale PyTorch, TF, and HuggingFace across clusters, boosting efficiency and fault tolerance.
deepspeed
orchestra-research/ai-research-skills
5.2k
This skill provides expert guidance for distributed training with DeepSpeed, covering ZeRO, pipeline parallelism, FP16/BF16/FP8, and optimization best
bigcode-evaluation-harness
orchestra-research/ai-research-skills
5.2k
This skill benchmarks code generation models across 15+ tasks, providing pass@k metrics and multi-language evaluation for robust code quality.
segment-anything
orchestra-research/ai-research-skills
5.2k
This skill enables zero-shot image segmentation with the Segment Anything Model, allowing prompts by points, boxes, or masks and automatic mask generation.
gguf
orchestra-research/ai-research-skills
5.2k
This skill helps you deploy AI models efficiently on consumer hardware using GGUF quantization for flexible 2-8 bit inference.
pyvene
orchestra-research/ai-research-skills
5.2k
This skill helps you apply causal interventions to PyTorch models with pyvene, enabling tracing, patching, IIT, and hypothesis testing.
hqq
orchestra-research/ai-research-skills
5.2k
This skill enables calibration-free 4/3/2-bit model quantization using HQQ for fast, deployment-ready quantization with HuggingFace and vLLM.
phoenix
orchestra-research/ai-research-skills
5.2k
This skill helps you instrument, trace, evaluate, and monitor LLM applications with Phoenix for debugging, testing, and real-time observability.
long-context
orchestra-research/ai-research-skills
5.2k
This skill helps extend transformer context windows for long documents using RoPE, YaRN, ALiBi, and position interpolation to improve efficiency and
torchtitan
orchestra-research/ai-research-skills
5.2k
This skill enables scalable pretraining of large language models using PyTorch Torchtitan 4D parallelism across GPUs, delivering faster training with efficient
nemo-evaluator
orchestra-research/ai-research-skills
5.2k
This skill helps you benchmark LLMs across 100+ benchmarks with containerized, scalable evaluation on local Docker, Slurm HPC, or cloud platforms.
mlflow
orchestra-research/ai-research-skills
5.2k
This skill helps you manage end-to-end ML lifecycles with MLflow, including experiment tracking, model registry, and reproducible deployments across frameworks.
knowledge-distillation
orchestra-research/ai-research-skills
5.2k
This skill helps you compress large language models via knowledge distillation, preserving performance while enabling smaller, faster open-source deployments.