Back to tags
Tag

Agent Skills with tag: Model

20 skills match this tag. Use tags to discover related Agent Skills and explore similar workflows.

distributed-training-megatron-core

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

[Megatron-CoreLarge-ScaleTrainingNVIDIA
Orchestra Research
Orchestra Research
33,1943,891

emerging-techniques-knowledge-distillation

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

[EmergingTechniquesKnowledgeDistillation
Orchestra Research
Orchestra Research
33,1943,891

emerging-techniques-model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

[EmergingTechniquesModelMerging
Orchestra Research
Orchestra Research
33,1943,891

emerging-techniques-model-pruning

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

[EmergingTechniquesModelPruning
Orchestra Research
Orchestra Research
33,1943,891

evaluation-lm-evaluation-harness

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

[EvaluationLMEvaluationHarness
Orchestra Research
Orchestra Research
33,1943,891

mechanistic-interpretability-nnsight

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

[nnsightNDIFRemoteExecution
Orchestra Research
Orchestra Research
33,1943,891

mlops-mlflow

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

[MLOpsMLflowExperimentTracking
Orchestra Research
Orchestra Research
33,1943,891

mlops-tensorboard

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

[MLOpsTensorBoardVisualizationTraining
Orchestra Research
Orchestra Research
33,1943,891

mlops-weights-and-biases

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

[MLOpsWeightsAndBiases
Orchestra Research
Orchestra Research
33,1943,891

model-architecture-rwkv

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

[RWKVModelArchitectureRNN
Orchestra Research
Orchestra Research
33,1943,891

optimization-gguf

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

[GGUFQuantizationllama.cppCPU
Orchestra Research
Orchestra Research
33,1943,891

optimization-hqq

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

[QuantizationHQQOptimizationMemory
Orchestra Research
Orchestra Research
33,1943,891

weights-and-biases

W&B: log ML experiments, sweeps, model registry, dashboards.

[MLOpsWeightsAndBiases
delorenj
delorenj
176

evaluating-llms-harness

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

[EvaluationLMEvaluationHarness
delorenj
delorenj
176

evaluating-llms-harness

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

[EvaluationLMEvaluationHarness
poorrican
poorrican
0

weights-and-biases

W&B: log ML experiments, sweeps, model registry, dashboards.

[MLOpsWeightsAndBiases
poorrican
poorrican
0

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

[GGUFQuantizationllama.cppCPU
poorrican
poorrican
0

evaluating-llms-harness

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

[EvaluationLMEvaluationHarness
PoorRican
PoorRican
0

weights-and-biases

W&B: log ML experiments, sweeps, model registry, dashboards.

[MLOpsWeightsAndBiases
PoorRican
PoorRican
0

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

[GGUFQuantizationllama.cppCPU
PoorRican
PoorRican
0