Packs
1 packResults for “embedding-model”
15 skills
drnabeelkhan ai-engineer
Implements machine learning models, embeddings, and AI-powered features with ethical considerations, including model selection, integration, and monitoring.
2
orchestra-research sentence-transformers
Generate high-quality sentence and text embeddings for semantic similarity, clustering, and retrieval using 5000+ pre-trained models. Supports multilingual and domain-specific embeddings for RAG and semantic search.
10.4k · bundle
majiayu000 esm
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.
567 · bundle
qhjqhj00 tensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard.
3 · bundle
nvidia tao-finetune-cosmos-embed
Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.
2.2k · bundle
More results
nvidia tao-train-reid
Trains, evaluates, exports, and runs inference for person re-identification models using TAO, learning discriminative embeddings for cross-camera matching.
2.2k · bundle
huggingface hf-cloud-sagemaker-deployment-planner
Plans and coordinates the deployment of a model to Amazon SageMaker AI, selecting the appropriate pathway (real-time, serverless, async, batch, or Bedrock CMI) based on model type, traffic, latency, and cost constraints.
10.8k
qhjqhj00 umap-learn
Reduce high-dimensional data with UMAP for visualization, clustering preprocessing, and supervised or semi-supervised learning, including parameter tuning guidance.
3 · bundle
orchestra-research moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace, covering architectures, routing, load balancing, and expert parallelism.
10.4k · bundle
orchestra-research model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining, covering SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.
10.4k · bundle
mukul975 detecting-data-and-model-poisoning
Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.
24.6k · bundle
lingxling geniml
Trains machine learning models on genomic interval data from BED files, including region embeddings, single-cell ATAC-seq analysis, and consensus peak building.
253 · bundle
k-dense-ai geniml
Train unsupervised machine learning models on genomic interval data from BED files, including region embeddings, single-cell ATAC-seq analysis, and consensus peak building.
30.2k · bundle
qhjqhj00 tpr-fpr
Evaluates speaker verification models by computing true positive rate at fixed false positive rate thresholds, probing embedding space separation of same-speaker versus different-speaker pairs.
3
nvidia tao-finetune-clip
Fine-tune and deploy CLIP vision-language models for zero-shot classification, image-text retrieval, and embedding extraction with ONNX and TensorRT support.
2.2k · bundle