244 skills · sorted by relevance
Choose a serving container for models deployed on SageMaker. Match the model type to a compatible image, retrieve its address from the AWS catalog, and check regional availability, CPU or GPU variants, and required host settings.
Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.
Keep chat-ui model settings aligned with the HuggingFace router. Add descriptions for newly available models, check reasoning support, enable artifact panels based on model size, and remove settings for models no longer served.
Prepare text for language models using HuggingFace Tokenizers, which splits text into model-readable units. Train custom vocabularies, process batches, track original text positions, and configure input lengths for use with transformers.
Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.
Adapt machine learning training to run across multiple GPUs or machines with Ray Train. Covers changes to existing code, comparing training settings with Ray Tune, and saving checkpoints so training can resume after failures.
Add support for a new language model in MNN, from downloading and analyzing it to mapping model fields, comparing intermediate results, and exporting files. Follow staged tests, with additional paths for image, audio, and unusual architectures.
Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.
Apply HQQ quantization, which stores language model weights using fewer bits without calibration examples. Covers precision settings, inference backends, saving compressed models, deployment with HuggingFace Transformers or vLLM, and further training with LoRA.
Manage Hugging Face Hub through the hf command line tool. Download and upload models or datasets, organize cloud storage, manage authentication and local caches, run scheduled jobs, and deploy or maintain model inference services.
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
The English summary is being prepared. Showing the original description.
Use the hf command-line tool to find, download, and upload models and datasets on Hugging Face Hub. The guide also covers repository management, hosted computing resources, local cache maintenance, and automation options.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Compress LLM weights using HQQ quantization, which stores weights with fewer bits without calibration datasets. Follow workflows for precision settings, model saving, inference integration, and LoRA fine-tuning of quantized models.
Reduce GPU memory use by loading language models in 8-bit or 4-bit formats with bitsandbytes and HuggingFace Transformers. Includes configuration examples, QLoRA fine-tuning of compressed models, and optimizers that reduce memory needed during training.
Adapt existing PyTorch training scripts to run across multiple GPUs or machines with Accelerate. This skill covers device setup, distributed training configuration, and mixed precision, which uses lower-precision numbers to reduce memory use.
Helps adapt machine learning training to multiple GPUs and machines with Ray Train. Covers resource allocation, recovery from saved training states, and Ray Tune searches that compare settings such as learning rate and batch size.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Build image generation workflows in Python with Stable Diffusion and HuggingFace Diffusers. The guide covers text prompts, transforming existing images, replacing selected regions, controlling composition, applying learned styles, and adjusting memory use during generation.
Build and train Mixture of Experts models, which activate selected specialist networks for each input. Use DeepSpeed or HuggingFace workflows to configure routing, balance workloads, distribute experts across GPUs, and optimize inference.
Adapt PyTorch training scripts for multiple GPUs or machines with Accelerate. This skill guides code changes, configuration, and launch commands, including mixed precision, which combines numerical formats, and DeepSpeed or FSDP integration for distributed training.
Build text, image, and audio features in JavaScript using machine learning models that run in browsers or server runtimes. Covers model selection, execution settings, caching, and memory cleanup without requiring a Python server.
Train Mixture of Experts models, which activate selected specialist networks for each input. The skill guides architecture, input routing, workload balancing, and GPU distribution using DeepSpeed or HuggingFace, with examples for training configuration and inference optimization.
Build image generation workflows in Python with Stable Diffusion and HuggingFace Diffusers. The guide covers text prompts, transforming existing images, replacing selected regions, controlling composition, applying learned styles, and adjusting memory use during generation.