Reverse Dependencies of sentencepiece
The following projects have a declared dependency on sentencepiece:
- oceanai — OCEAN-AI
- ochat — An efficient framework for training and serving top-tier, open-source conversational LLMs.
- ocr_translate-hugging_face — Plugins to enable usage of HuggingFace Models in ocr_translate
- octopod — General purpose multi-task classification library
- offline-translator — Offline Translator GUI using Opus-MT.
- ohmeow-blurr — A library designed for fastai developers who want to train and deploy Hugging Face transformers
- omdenalore — AI for Good library
- OmniEvent — A tookit for event extraction.
- OmniGenome — OmniGenome: A comprehensive toolkit for genome analysis.
- op-text — Thin wrapper around HuggingFace Transformers sequence classification models for ease of use
- open-clip-torch — OpenCLIP
- open-flamingo — An open-source framework for training large multimodal models
- open-gpt-torch — An open-source cloud-native of large multi-modal models (LMMs) serving framework.
- openagent-py — no summary
- openagentos — no summary
- openAMS — no summary
- openbb-chat — Deep learning package to add chat capabilities to OpenBB
- opendelta — An open source framework for delta learning (parameter efficient learning).
- openelm-pytorch — openelm-pytorch
- OpenLLM — OpenLLM: Operating LLMs in production
- openlora — no summary
- openprompt — An open source framework for prompt-learning.
- openspeech-core — Open-Source Toolkit for End-to-End Automatic Speech Recognition
- openspeech-py — Open-Source Toolkit for End-to-End Automatic Speech Recognition
- openspeechs — Open-Source Toolkit for End-to-End Automatic Speech Recognition
- optimum-furiosa — Optimum Furiosa is the interface between the 🤗 Transformers library and Furiosa NPUs such as Furiosa Warboy. It provides a set of tools enabling easy model loading and inference for different downstream tasks for Furiosa NPU.
- optimum-graphcore — Optimum Library is an extension of the Hugging Face Transformers library, providing a framework to integrate third-party libraries from Hardware Partners and interface with their specific functionality.
- optimum-habana — Optimum Habana is the interface between the Hugging Face Transformers and Diffusers libraries and Habana's Gaudi processor (HPU). It provides a set of tools enabling easy model loading, training and inference on single- and multi-HPU settings for different downstream tasks.
- optimum-intel — Optimum Library is an extension of the Hugging Face Transformers library, providing a framework to integrate third-party libraries from Hardware Partners and interface with their specific functionality.
- optimum-neuron — Optimum Neuron is the interface between the Hugging Face Transformers and Diffusers libraries and AWS Tranium and Inferentia accelerators. It provides a set of tools enabling easy model loading, training and inference on single and multiple neuron core settings for different downstream tasks.
- optimum-transformers — Accelerated nlp pipelines using Transformers, Optimum and ONNX Runtime
- optimumEasyNMT — Easy to use state-of-the-art Neural Machine Translation
- orkgnlp — Python package wrapping the ORKG NLP Services.
- osc-llm — 大模型训练,评估,推理,部署工具
- ought-ice — Interactive Composition Explorer
- ovos-translate-plugin-nllb — OVOS translation module for No Language Left Behind
- p2x_corporate_engine — P2x model wrapper for corporate injection
- paddle-serving-app — Paddle Serving Package for saved model with PaddlePaddle
- paddlenlp — Easy-to-use and powerful NLP library with Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including Neural Search, Question Answering, Information Extraction and Sentiment Analysis end-to-end system.
- pai-easynlp — PAI EasyNLP Toolkit
- paintmind — no summary
- paragraph2actions — Extraction of actions from experimental procedures
- parallel-corpus-mnbvc — parallel corpus dataset from the pypi repository of the mnbvc project
- paraphrase-metrics — Paraphrase Metrics
- parasol-nlp — Korean tokenizer with character decomposition
- pcl-pangu — pcl_pangu
- pdf-struct — Logical structure analysis of visually structured documents.
- petals — Easy way to efficiently run 100B+ language models without high-end GPUs
- pgml-extension — Simple machine learning in PostgreSQL.
- phenaki-pytorch — Phenaki - Pytorch
- phi-torch — Phi - Pytorch
- phold — Phage Annotations using Protein Structures
- plain-transformers — one more transformers lib
- pleonasty — A very simple abstraction for LLMs to get single responses to a given input.
- poetry-190048221 — no summary
- poetry-190048221-rodrigo — no summary
- poetry-docs — no summary
- poetry-gces — no summary
- poetry-ger — no summary
- poetry-sirius — no summary
- poetry-victordscabral-gces — Trabalho individual de GCES
- poetry-vital14 — no summary
- poetrygces-pedro-vieira — no summary
- pop-ml — Machine learning library for pop projects
- postocr-3stages — Post-OCR correction in 3 stages.
- pou-shap — A unified approach to explain the output of any machine learning model.
- ppi-origami — Tools for protein-protein interaction datasets.
- praxis — Functionalities such as a layers for building neural networks in Jax.
- pre-ai-python — Microsoft AI Python Package
- prenlp — Preprocessing Library for Natural Language Processing
- primeqa — State-of-the-art Question Answering
- prompt2model — A library for distilling models from prompts.
- promptbench — PromptBench is a powerful tool designed to scrutinize and analyze the interaction of large language models with various prompts. It provides a convenient infrastructure to simulate **black-box** adversarial **prompt attacks** on the models and evaluate their performances.
- promptcraft — PromptCraft: A Prompt Perturbation Toolkit for Prompt Robustness Analysis
- promptflow-gui — Create flowcharts to control LLMs
- protenc — Extract protein embeddings from protein language models.
- punctuators — Punctuators and such
- py-data-juicer — A One-Stop Data Processing System for Large Language Models.
- py-data-modori — LMOps Tool for Korean
- pyabsa — This tool provides the state-of-the-art models for aspect term extraction (ATE), aspect polarity classification (APC), and text classification (TC).
- pyannotators-trfclassifier — Classifier based on Huggingface Text Classification pipeline
- pyannotators-zeroshotclassifier — Annotator based on Huggingface transformers zero-shot classification pipeline
- pyBibX — A Bibliometric and Scientometric Library Powered with Artificial Intelligence Tools
- pyconverters-speech — Speech recognition converter based on Huggingface pipeline
- pydata-wrangler — Wrangle messy data into pandas DataFrames, with a special focus on text data and natural language processing
- pyfastedit — Editing large language models within 10 seconds
- pyformatters-summarizer — Formatter based on Huggingface transformers summarization pipeline
- pyiqa — PyTorch Toolbox for Image Quality Assessment
- pyllama — 🦙 LLaMA: Open and Efficient Foundation Language Models in A Single GPU
- pyllmsearch — LLM Powered Advanced RAG Application
- pypi-poetry — no summary
- pyprocessors-q_and_a — Processor based on Huggingface transformers Q&A pipeline
- pyreft — REFT: Representation Finetuning for Language Models
- pyrift — no summary
- pyserini-install — A Python toolkit for reproducible information retrieval research with sparse and dense representations
- pytext-nlp — pytorch modeling framework and model zoo for text models
- pytorch-quik — functions to make working in pytorch quik-er
- pytorch-transformers — Repository of pre-trained NLP Transformer models: BERT & RoBERTa, GPT & GPT-2, Transformer-XL, XLNet and XLM
- pytorch-transformers-pvt-nightly — Repository of pre-trained NLP Transformer models: BERT & RoBERTa, GPT & GPT-2, Transformer-XL, XLNet and XLM
- pyvene — Use Activation Intervention to Interpret Causal Mechanism of Model