Reverse Dependencies of datasets
The following projects have a declared dependency on datasets:
- friendli-client — Client of Friendli Suite.
- ft-suite — A fine-tuning suite based on Transformers and LoRA.
- fundialogues — A library of datasets, LLM tooling, and open source models that can be used for training and inference for prototyping purposes.
- future-shot — FutureShot: Few-Shot Learning for high-dimensional classification problems
- galactic-ai — Curate, annotate, and clean massive unstructured text datasets for machine learning and AI systems.
- galahad — Machine learning model server that can predict AND train
- gantry — Gantry Python Library
- Gao-Anime — AI Head
- garak — LLM vulnerability scanner
- gcgc — GCGC is a preprocessing library for biological sequence model development.
- gem-metrics-fork — GEM Challenge metrics
- general-text-classifier — General Text Classification Library
- genienlp — no summary
- geniusrise-audio — audio bolts for geniusrise
- geniusrise-huggingface — Huggingface bolts for geniusrise
- geniusrise-openai — Openai bolts for geniusrise
- geniusrise-text — Text bolts for geniusrise
- geniusrise-vision — Huggingface bolts for geniusrise
- gentab — A synthetic tabular data generation library.
- gft — GFT (general fine-tuning) A Little Language for Deepnets: 1-line programs for fine-tuning, inference and more
- gft-cpu — GFT (general fine-tuning) A Little Language for Deepnets: 1-line programs for fine-tuning, inference and more
- gigachain — Building applications with LLMs through composability
- gigachain-community — Community contributed LangChain integrations.
- git-t5 — Open source machine learning framework for training T5 models on source code in JAX/Flax.
- git4net — My short description for my project.
- glmtuner — Fine-tuning ChatGLM-6B with PEFT
- goldenretriever-core — Dense Retriever
- goodai-ltm — A text memory meant to be used with conversational language models.
- gperc — General purpose perceiver architectures!
- gpfy — Gaussian process with spherical harmonic features in JAX
- gps-babel-tower — Babel Tower NLP Library
- gpt3-torch — GPT3 - Pytorch
- gpt4-torch — GPT4 - Pytorch
- gramex — Gramex: Low Code Data Solutions Platform
- grandmaster — no summary
- graph-weather — Weather Forecasting with Graph Neural Networks
- green-bit-llm — A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.
- gritlm — GritLM
- grouphug — GroupHug is a library with extensions to 🤗 transformers for multitask language modelling.
- gt4sd — Generative Toolkit for Scientific Discovery (GT4SD).
- gt4sd-molformer — Molformer's submodule of GT4SD.
- gt4sd-trainer-hf-pl — Transformers trainer submodule of GT4SD.
- h2ogpt — no summary
- hackathon-evaluation-rag — no summary
- halitefn — Acceleration framework for Human Alignment Learning
- halludetector — Hallucination detection package
- happytransformer — Happy Transformer makes it easy to fine-tune NLP Transformer models and use them for inference.
- healthsageai — HealthSage AI LLMs, Healthcare genAI platform
- heart-library — Hardened Extension of the Adversarial Robustness Toolbox (HEART) supports assessment of adversarial AI vulnerabilities in Test & Evaluation workflows.
- helmet — no summary
- hetseq — Distributed GPU Training on Heterogeneous Infrastructureg
- hezar — Hezar: The all-in-one AI library for Persian, supporting a wide variety of tasks and modalities!
- hf-clean-benchmarks — This repository contains code for cleaning your training data of benchmark data to help combat data snooping.
- hf-dataset-structurer — A package to structure datasets in the Hugging Face Hub
- hf-endpoints-emulator — Emulator for Custom Handlers for Inference Endpoints
- HF-fastup — Fast upload in parallel large datasets to HuggingFace Datasets hub.
- hierarchy-transformers — Language models as hierarchy encoders.
- hk-nlp — personal package
- hugdatafast — The elegant bridge between hugginface data and fastai
- hugg — My short description for my project.
- huggingface-tool — Toolkit for managing huggingface models and datasets
- huggingsound — HuggingSound: A toolkit for speech-related tasks based on HuggingFace's tools.
- hugit — Hugit
- hurricore — A deep learning framework based on PyTorch and Accelerate.
- hyfi — Hydra Fast Interface (Hydra and Pydantic based interface framework)
- hyped — TODO
- iblm — Inductive-bias Learning
- ibltuning — no summary
- ibm-generative-ai — IBM Generative AI is a Python library built on IBM's large language model REST interface.
- il-datasets — A package for creating IL datasets
- image-reward — ImageReward
- imagen-pytorch — Imagen - unprecedented photorealism × deep level of language understanding
- imaginaryNLP — Imaginary Embeddings for NLP
- imitation — Implementation of modern reward and imitation learning algorithms.
- imodelsx — Library to explain a dataset in natural language.
- indexpaper — indexpaper - library to index papers with vector databases
- indobenchmark-toolkit — Indobenchmark toolkit for supporting IndoNLU and IndoNLG
- indomain — no summary
- inferno-ml — A package for accelerating deep learning inference
- inranker — no summary
- inseq — Interpretability for Sequence Generation Models 🔍
- inspect-ai — Framework for large language model evaluations
- instanovo — De novo sequencing with InstaNovo
- instruct-goose — Implementation of Reinforcement Learning from Human Feedback (RLHF)
- instruct-qa — Empirical evaluation of retrieval-augmented instruction-following models.
- instructlab — CLI for interacting with InstructLab
- instructor-embedders-haystack — Haystack 2.x component to embed strings and Documents using Instructor embedding model.
- integral_deid — PHI taggging and redaction
- intel-transfer-learning-tool — Intel® Transfer Learning Tool
- intel-xai — Intel® Explainable AI Tools
- internet-ml — Internet-ML: Allowing ML to connect to the internet
- internet-nlp — Allowing NLPs to connect to the internet
- interpres — Translate from one language to another.
- invokeai — An implementation of Stable Diffusion which provides various new features and options to aid the image generation process
- item-matching — A name matching package
- iva-mt — A machine translation library utilizing m2m100 models, equipped with features for generating diverse verb variants via VerbNet and Conditional Beam Search to enrich Virtual Assistant training sets.
- jac-nlp — no summary
- jax-dataloader — Dataloader for jax
- jax-relax — JAX-based Recourse Explanation Library
- jiant — State-of-the-art Natural Language Processing toolkit for multi-task and transfer learning built on PyTorch.