Reverse Dependencies of optimum

The following projects have a declared dependency on optimum:

• airllm — AirLLM allows single 4GB GPU card to run 70B large language models without quantization, distillation or pruning.
• airoboros — Updated and improved implementation of the self-instruct system.
• aivoifu — Easy and fast AI Waifu voice generation
• alpaca-eval — AlpacaEval : An Automatic Evaluator of Instruction-following Models
• amf-fast-inference — uses pruning and quatisation to make inference speed faster
• asian-mtl — Seamlessly translate East Asian texts with deep learning models.
• auto-coder — AutoCoder: AutoCoder
• autogluon.timeseries — Fast and Accurate ML in 3 Lines of Code
• azureml-acft-accelerator — Contains the acft accelerator package used in script to build the azureml components.
• bpm-ai-inference — Inference and server for local AI implementations of bpm-ai-core abstractions.
• chatdocs — Chat with your documents offline using AI.
• classy-classification — Have you every struggled with needing a Spacy TextCategorizer but didn't have the time to train one from scratch? Classy Classification is the way to go!
• CLIP-API-service — Build AI applications with any CLIP models - embed image and sentences, object recognition, visual reasoning, image classification and reverse image search
• dalpha-ai — no summary
• dalpha-ai-cpu — no summary
• datadreamer.dev — Prompt. Generate Synthetic Data. Train & Align Models.
• dbgpt — DB-GPT is an experimental open-source project that uses localized GPT large models to interact with your data and environment. With this solution, you can be assured that there is no risk of data leakage, and your data is 100% private and secure.
• easy-transformers — Utils for dealing with transformers
• exciton — Natural Language Processing by the Exciton Research
• ezlocalai — ezlocalai is an easy to set up local multimodal artificial intelligence server with OpenAI Style Endpoints.
• fastnn — A python library and framework for fast neural network computations.
• finetuning-suite — A fine-tuning suite based on Transformers and LoRA.
• flying-delta-legacy — Interface between LLMs and your data
• ft-suite — A fine-tuning suite based on Transformers and LoRA.
• geniusrise-audio — audio bolts for geniusrise
• geniusrise-text — Text bolts for geniusrise
• geniusrise-vision — Huggingface bolts for geniusrise
• gentopia — Gentopia provides extensive utilities to assembles ALM agents driven by configs.
• goldenretriever-core — Dense Retriever
• gptq-Quantizer — A Python package for GPTQ quantization
• h2ogpt — no summary
• icortex — Jupyter kernel that can generate Python code from natural language prompts
• infinity_emb — Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of sentence-transformer models and frameworks.
• insanely-fast-whisper — An insanely fast whisper CLI
• kozmoserver-huggingface — HuggingFace runtime for KozmoServer
• langport — A large language model serving platform.
• lexikos — A collection of pronunciation dictionaries and neural grapheme-to-phoneme models.
• lighteval — A lightweight and configurable evaluation package
• llama-index-core — Interface between LLMs and your data
• llama-index-embeddings-huggingface-optimum — llama-index embeddings huggingface optimum integration
• llama-index-embeddings-huggingface-optimum-intel — llama-index embeddings Optimum Intel integration
• llama-index-embeddings-openvino — llama-index embeddings openvino integration
• llama-index-legacy — Interface between LLMs and your data
• llama-index-llms-openvino — llama-index llms openvino integration
• llama-index-postprocessor-openvino-rerank — llama-index postprocessor openvino rerank integration
• llama-recipes — Llama-recipes is a companion project to the Llama 2 model. It's goal is to provide examples to quickly get started with fine-tuning for domain adaptation and how to run inference for the fine-tuned models.
• llm-guard — LLM-Guard is a comprehensive tool designed to fortify the security of Large Language Models (LLMs). By offering sanitization, detection of harmful language, prevention of data leakage, and resistance against prompt injection attacks, LLM-Guard ensures that your interactions with LLMs remain safe and secure.
• llm-serve — An LLM inference solution to quickly deploy productive LLM service
• llmanalyst — Talk to your CSV data with your huggingface llm models
• llmpool — Large Language Models' pool management library
• llmtuner — Easy-to-use LLM fine-tuning framework
• lm-eval — A framework for evaluating language models
• lmwrapper — Wrapper around language model APIs
• luis-v-subtitler — A Python package to use AI to subtitle any video in any language
• mase-tools — Machine-Learning Accelerator System Exploration Tools
• mlserver-huggingface — HuggingFace runtime for MLServer
• mlserver-huggingface-striveworks — HuggingFace runtime for MLServer
• mmda — MMDA - multimodal document analysis
• ms-swift — Swift: Scalable lightWeight Infrastructure for Fine-Tuning
• nendo-plugin-textgen — A text generation plugin using local LLMs or other text generation methods. Builds on top of `transformers` by Hugging Face.
• olive-ai — Olive is an easy-to-use hardware-aware model optimization tool that composes industry-leading techniques across model compression, optimization, and compilation.
• openbb-chat — Deep learning package to add chat capabilities to OpenBB
• OpenLLM — OpenLLM: Operating LLMs in production
• optim-sentence-transformrs — API to optimize SentenceTransformer models using ONNX/Optimum and perform inference using the same `model.encode` API.
• optimum-amd — 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-deepsparse — Optimum DeepSparse is an extension of the Hugging Face Transformers library that integrates the DeepSparse inference runtime. DeepSparse offers GPU-class performance on CPUs, making it possible to run Transformers and other deep learning models on commodity hardware with sparsity. Optimum DeepSparse provides a framework for developers to easily integrate DeepSparse into their applications, regardless of the hardware platform.
• 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-haystack — Component to embed strings and Documents using models loaded with the HuggingFace Optimum library. This component is designed to seamlessly inference models using the high speed ONNX runtime.
• 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-nvidia — Optimum Nvidia is the interface between the Hugging Face Transformers and NVIDIA GPUs. "
• optimum-transformers — Accelerated nlp pipelines using Transformers, Optimum and ONNX Runtime
• optimumEasyNMT — Easy to use state-of-the-art Neural Machine Translation
• ouroboros-hf-text-generation — Simple hugging face text generation utility package with multiple prompt format support and history.
• papermage — Papermage. Casting magic over scientific PDFs.
• pix2text — An Open-Source Python3 tool for recognizing layouts, tables, math formulas, and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations.
• quantizetk — quantizetk
• raga-llm-eval — Package for LLM Evaluation
• raga-llm-hub — Package for LLM Evaluation
• scandeval — Evaluation of pretrained language models on mono- or multilingual language tasks.
• sft-dpo-qlora — SFT-DPO-QLora Trainer Package
• simple-generation — A python package to run inference with HuggingFace checkpoints wrapping many convenient features.
• speechtoolkit — ML for Speech presents SpeechToolkit, a unified, all-in-one toolkit for TTS, ASR, VC, & other models.
• text2text — Text2Text: Crosslingual NLP/G toolkit
• textsum — utility for using transformers summarization models on text docs
• textwiz — An even simpler way to use open-source LLMs.
• transformers-crf — Transformers CRF: CRF Token Classification for Transformers
• vec2text — convert embedding vectors back to text
• wafl-llm — A hybrid chatbot - LLM side.
• whisper-s2t — An Optimized Speech-to-Text Pipeline for the Whisper Model.
• xllm — Simple & Cutting Edge LLM Finetuning
• zyh — Easily show off amazing scripys by zyh