Model Training & Fine-tuning

nvidia Bundle

Create Earth2Studio prognostic model wrappers that time-step weather forecasts forward, with triple-inheritance classes, tests, and documentation.

orchestra-research Bundle

Quantize large language models to 4-bit using activation-aware weight quantization, achieving ~3x speedup with minimal accuracy loss for deployment on limited GPU memory.

orchestra-research Bundle

Convert and quantize models to GGUF format for efficient CPU/GPU inference with llama.cpp, supporting 2-8 bit quantization and Apple Silicon acceleration.

orchestra-research Bundle

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments.

orchestra-research Bundle

Train large-scale MoE models with FP8/INT4 low-precision RL, speculative decoding, and train-inference alignment using the miles framework.

orchestra-research Bundle

Run ML training and batch jobs across multiple clouds with automatic cost optimization, spot instance recovery, and unified orchestration.

orchestra-research Bundle

Train reinforcement learning models using torchforge, Meta's PyTorch-native RL library for scalable, algorithm-focused experimentation with GRPO, DAPO, and custom loss functions.

orchestra-research Bundle

Provides expert guidance for fine-tuning LLMs with LLaMA-Factory, covering WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, and multimodal support.

orchestra-research Bundle

Train and use SentencePiece tokenizers for multilingual NLP, supporting BPE and Unigram algorithms with raw Unicode text.

orchestra-research Bundle

Pretrains large language models from scratch using PyTorch-native distributed training with 4D parallelism (FSDP2, TP, PP, CP) and Float8 support on H100 GPUs.

orchestra-research Bundle

Scales machine learning training from single GPU to multi-node clusters with minimal code changes. Supports PyTorch, TensorFlow, and HuggingFace with built-in hyperparameter tuning, fault tolerance, and elastic scaling.

orchestra-research Bundle

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag) using standardized prompts and metrics. Supports HuggingFace, vLLM, and API backends.

orchestra-research Bundle

Organizes PyTorch code with a Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks, and minimal boilerplate. Scales from laptop to supercomputer with the same code.

franks-intellab Bundle

End-to-end Kaggle competition workflow for scored submissions, covering code competitions, validation, metrics, public notebook/discussion intel, tabular/text/image modeling, tuning, ensembling, multi-notebook architectures, Kaggle GPU offload, and hidden-test debugging.

majiayu000 Bundle

Generates and analyzes proteins using ESM3 and ESM C language models, covering sequence generation, structure prediction, inverse folding, embeddings, and function conditioning with local or cloud-based Forge API inference.

majiayu000 Bundle

Provides scikit-learn compatible algorithms for time series machine learning, including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search.

dvcrn Skill

Classifies situations into 256 binary states and maps each to a prescribed action, reporting the pattern, decimal, name, range, and action to execute.

lingxling Bundle

Generates and analyzes protein sequences and structures using ESM3, ESMC, and ESMFold2, with support for local and cloud inference.

lingxling Bundle

Provides guidance for using RDKit to read and write molecular structures, calculate descriptors, generate fingerprints, perform substructure searches, and handle chemical reactions.

lingxling Skill

Estimates memory requirements for running Hugging Face models, including optional KV cache, using HTTP range requests without downloading weights.

drnabeelkhan Skill

Implements machine learning models, embeddings, and AI-powered features with ethical considerations, including model selection, integration, and monitoring.

lord1egypt Skill

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on limited GPU memory.

luokai0 Bundle

Provides domain knowledge on the Causal Dynamics Architecture (CDA), an alternative AI computing architecture based on causal graphs and Hamiltonian dynamics, with references for deep dives.

clawbio Bundle

Predicts chromatin state across 919 tracks (histone marks, DNase, TF binding) for DNA sequences via the hosted Genomic Intelligence API, producing a report and JSON results.

samyakjhaveri Skill

Launches a model evaluation batch with parameter collection, pre-flight checks, execution, and post-run analysis for interactive or foreground runs.

neuralblitz Skill

Scales AI and Python applications across clusters with distributed computing primitives for ML workloads.

neuralblitz Skill

Guides the implementation of ethical AI principles, including fairness auditing, bias mitigation, explainability, accountability, and privacy protection in machine learning systems.

neuralblitz Skill

Implements and applies algorithms concepts, designs solutions using algorithmic principles, and optimizes performance for algorithm implementations.

oyi77 Skill

Designs and implements RAG pipelines, covering document chunking, embedding strategies, hybrid search, answer synthesis with source attribution, and evaluation using RAGAS metrics.

tools-only Bundle

Aeon provides forecasting algorithms for predicting future time series values.

phoroth Skill

Orchestrates AI/ML workflows for building LLM applications, RAG systems, AI agents, and ML pipelines, covering design, integration, observability, and security.

phoroth Skill

Formalizes narrative technical documents into structured mathematical problem specifications with variables, constraints, objectives, and uncertainty, citing evidence and flagging missing information.

qhjqhj00 Bundle

Quantize LLMs to 8/4/3/2/1-bit precision without calibration data, using multiple backends and HuggingFace/vLLM integration.

qhjqhj00 Skill

Validates the Emotional Attitude Score (EAS) metric by measuring its consistency with human judgment on word-level sentiment polarity, using the AmbGIMT dataset and pairwise score comparisons.

qhjqhj00 Skill

Computes the Receiver Operating Characteristic (ROC) metric using torchmetrics, supporting binary, multiclass, and multilabel tasks.

qhjqhj00 Skill

Computes the HARE Score, an entity- and relation-centric metric for evaluating machine-generated histopathology reports against ground truth, using GatorTronS+SapBERT embeddings and relation F1.