{"library":"curated-transformers","type":"library","category":null,"description":"Curated Transformers is a PyTorch library offering a collection of transformer models and components, optimized for efficiency and integration. It provides a consistent API for popular models like MPT, Llama 2, Falcon, BERT, and ELECTRA, supporting features like generation, 8-bit/4-bit quantization, and Safetensor checkpoints. The latest version is 2.0.1, with releases occurring as needed for features and bug fixes, often with a focus on PyTorch compatibility.","language":"python","status":"active","version":"2.0.1","tags":["pytorch","transformers","nlp","llm","deep-learning","explosion"],"last_verified":"Sat May 23","install":[{"cmd":"pip install curated-transformers torch safetensors huggingface_hub","imports":["from curated_transformers.models import AutoCausalLM","from curated_transformers.models import AutoEncoder","from curated_transformers.models import AutoDecoder","from curated_transformers.tokenization import AutoTokenizer","from curated_transformers.generation import Generator"]}],"homepage":"https://curated-transformers.readthedocs.io","github":"https://github.com/explosion/curated-transformers","docs":null,"changelog":null,"pypi":"https://pypi.org/project/curated-transformers/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":30,"avg_install_s":72.3,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/curated-transformers/compatibility"}}