Transformers
技能 已验证 活跃This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
To enable AI agents to easily leverage pre-trained transformer models for a wide range of tasks across different modalities, simplifying model loading, inference, and fine-tuning.
功能
- Pipelines for quick inference across many tasks
- Loading and management of pre-trained transformer models
- Text generation with various decoding strategies
- Fine-tuning models on custom datasets using the Trainer API
- Tokenization for model input processing
使用场景
- Rapid prototyping of NLP and vision tasks
- Performing inference on custom datasets
- Adapting pre-trained models to specific domains
- Integrating advanced AI capabilities into agent workflows
非目标
- Building models from scratch without pre-trained foundations
- Performing tasks outside the scope of transformer model capabilities
- Replacing the core Hugging Face libraries directly
工作流
- Load tokenizer and model
- Preprocess input data
- Perform inference or training
- Postprocess output
先决条件
- Huggingface token for some models
Versioning
- info:Release ManagementThe SKILL.md frontmatter has a 'license' field, but no explicit versioning information like SemVer is present. The repository uses GitHub commits directly.
Compliance
- info:GDPRThe skill processes text and data for model inference and training. Personal data may be submitted to the LLM depending on user input, but the skill itself does not specifically target or sanitize personal data beyond standard LLM processing.
Execution
- info:Pinned dependenciesThe installation instructions suggest using `uv pip install` but do not explicitly mention lockfiles or pinned versions for reproducibility.
安装
npx skills add K-Dense-AI/claude-scientific-skills通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
Transformers.js
99Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.
Segment Anything Model
99Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
Hugging Face Vision Trainer
99Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
PyTorch Lightning
100Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.
Nnsight Remote Interpretability
99Provides 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.
Huggingface Accelerate
99Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.