1182 个 · 按相关度排序
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
中文简介正在准备中。当前显示英语简介。
Integrate Flash Attention into transformer models to reduce processing time and GPU memory use for long sequences. Covers PyTorch integration, advanced attention options, and benchmarks that compare speed, memory use, and output accuracy.
中文简介正在准备中。当前显示英语简介。
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
中文简介正在准备中。当前显示英语简介。
Guides the use of RWKV, a language model architecture that carries information forward in a compact state. Covers streaming text generation, long document processing, fine-tuning, and memory comparisons with Transformers.
中文简介正在准备中。当前显示英语简介。
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
中文简介正在准备中。当前显示英语简介。
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
中文简介正在准备中。当前显示英语简介。
为处理长输入的Transformer模型接入Flash Attention，加快训练与推理中的注意力计算并减少GPU显存占用，涵盖安装、性能测量和输出比较。
Build and evaluate Mamba models for long sequences using state-space models, which summarize past inputs in an internal state. Covers setup, pretrained text generation, differences between Mamba-1 and Mamba-2, and speed comparisons with Transformers.
中文简介正在准备中。当前显示英语简介。
Implement Mamba, a model architecture that processes sequences through an internal state with computation scaling linearly with input length. Covers pretrained text generation, Mamba-1 and Mamba-2 configuration, speed comparisons with Transformers, and GPU memory troubleshooting.
中文简介正在准备中。当前显示英语简介。
Prepare large text collections for AI models with fast tokenizers, which split text into model inputs. Train custom vocabularies, trace tokens to original text positions, adjust input lengths, and integrate the results with transformers.
中文简介正在准备中。当前显示英语简介。
Guides you through setting up RWKV, generating text, processing long documents in chunks, and fine-tuning models. Explains how to carry context between steps and compare memory use with Transformer models.
中文简介正在准备中。当前显示英语简介。
Review CSS animations for properties that cause costly layout updates, then suggest changes using transform and opacity. Check how effects look across screen sizes and interaction states, including support for users who prefer reduced motion.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
"Apply the three-level framework of digital transformation — Digitization, Digitalization, and Digital Transformation — to diagnose and plan organizational change enabled by digital technologies. Use this skill when the user needs to assess an organization's digital maturity, distinguish between automating processes versus transforming business models, plan a DX roadmap, or when they ask 'where are we on digital transformation', 'is this digitization or real transformation', or 'how do we build a DX strategy'.".
中文简介正在准备中。当前显示原文说明。
Use Hugging Face Transformers to load pretrained models, generate text, and classify text, images, or audio. Prepare model inputs, control generation settings, and fine-tune models on custom datasets with the Trainer API.
中文简介正在准备中。当前显示英语简介。
Quantize diffusion transformers with NVIDIA ModelOpt, using FP8 or NVFP4 lower-precision numbers, and prepare the saved weights for SGLang Diffusion. Follow a workflow for loading, checking output quality, and comparing speed under matching conditions.
中文简介正在准备中。当前显示英语简介。
Generate embeddings, numerical representations of text or images, for meaning-based search, similarity comparisons, and document grouping. The skill guides model selection, multilingual processing, local execution, and integration with retrieval workflows.
中文简介正在准备中。当前显示英语简介。
Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.
中文简介正在准备中。当前显示英语简介。
Generate embeddings, numerical representations of text or images, for meaning-based search, similarity comparisons, and document grouping. The skill guides model selection, multilingual processing, local execution, and integration with retrieval workflows.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.
中文简介正在准备中。当前显示英语简介。
Build Apache Beam connectors that read and write external data. This guide covers Java implementation, schema support for structured records, access from Python and Go, Managed API integration, and testing.
中文简介正在准备中。当前显示英语简介。
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
中文简介正在准备中。当前显示原文说明。
Guide market prediction workflows with LSTM, Transformer, and N-BEATS models using neural-trader commands and result storage. It explicitly identifies version 2.8.11 outputs as placeholders, so they cannot be treated as fitted models or evidence of prediction accuracy.
中文简介正在准备中。当前显示英语简介。