Back to Marketplaces
active
20plugins
0skills
Orchestra Research

model-architecture

LLM architectures and implementations including LitGPT, Mamba, NanoGPT, and RWKV. Use when implementing, training, or understanding transformer and alternative architectures.

0 skills

No verified skills in this plugin.

infrastructure

GPU cloud and compute orchestration including Modal, Lambda Labs, and SkyPilot. Use when deploying training jobs or managing GPU resources.

0 skills

No verified skills in this plugin.

optimization

Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

0 skills

No verified skills in this plugin.

multimodal

Vision, audio, and multimodal models including CLIP, Whisper, LLaVA, BLIP-2, Segment Anything, Stable Diffusion, and AudioCraft. Use when working with images, audio, or multimodal tasks.

0 skills

No verified skills in this plugin.

ml-paper-writing

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Includes LaTeX templates, citation verification, reviewer guidelines, and writing best practices from top researchers.

0 skills

No verified skills in this plugin.

tokenization

Text tokenization for LLMs including HuggingFace Tokenizers and SentencePiece. Use when training custom tokenizers or handling multilingual text.

0 skills

No verified skills in this plugin.

fine-tuning

LLM fine-tuning frameworks including Axolotl, LLaMA-Factory, PEFT, and Unsloth. Use when fine-tuning models with LoRA, QLoRA, or full fine-tuning.

0 skills

No verified skills in this plugin.

mechanistic-interpretability

Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.

0 skills

No verified skills in this plugin.

data-processing

Data curation and processing at scale including NeMo Curator and Ray Data. Use when preparing training datasets or processing large-scale data.

0 skills

No verified skills in this plugin.

post-training

RLHF and preference alignment including TRL, GRPO, OpenRLHF, and SimPO. Use when aligning models with human preferences or training reward models.

0 skills

No verified skills in this plugin.

safety-alignment

AI safety and content moderation including Constitutional AI, LlamaGuard, and NeMo Guardrails. Use when implementing safety filters or content moderation.

0 skills

No verified skills in this plugin.

distributed-training

Multi-GPU and multi-node training including DeepSpeed, PyTorch FSDP, Accelerate, Megatron-Core, PyTorch Lightning, and Ray Train. Use when training large models across GPUs.

0 skills

No verified skills in this plugin.

evaluation

LLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.

0 skills

No verified skills in this plugin.

inference-serving

Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.

0 skills

No verified skills in this plugin.

mlops

ML experiment tracking and lifecycle including Weights & Biases, MLflow, and TensorBoard. Use when tracking experiments or managing models.

0 skills

No verified skills in this plugin.

agents

LLM agent frameworks including LangChain, LlamaIndex, CrewAI, and AutoGPT. Use when building chatbots, autonomous agents, or tool-using systems.

0 skills

No verified skills in this plugin.

rag

Retrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.

0 skills

No verified skills in this plugin.

prompt-engineering

Structured LLM outputs including DSPy, Instructor, Guidance, and Outlines. Use when extracting structured data or constraining LLM outputs.

0 skills

No verified skills in this plugin.

observability

LLM application monitoring including LangSmith and Phoenix. Use when debugging LLM apps or monitoring production systems.

0 skills

No verified skills in this plugin.

emerging-techniques

Advanced ML techniques including MoE Training, Model Merging, Long Context, Speculative Decoding, Knowledge Distillation, and Model Pruning. Use when implementing cutting-edge optimization or architecture techniques.

0 skills

No verified skills in this plugin.