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. 8GB vmem to run 405B Llama3.1.
• airoboros — Updated and improved implementation of the self-instruct system.
• airoot — Suite of generation models for text, image, audio and video.
• airunner — A Stable Diffusion GUI
• airunner-nexus — Run a socket server for AI models.
• 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.
• autogluon.timeseries — Fast and Accurate ML in 3 Lines of Code
• AutoRAG — Automatically Evaluate RAG pipelines with your own data. Find optimal structure for new RAG product.
• axolotl — LLM Trainer
• azarrot — An OpenAI compatible server, focusing on OpenVINO and IPEX-LLM usage.
• azureml-acft-accelerator — Contains the acft accelerator package used in script to build the azureml components.
• bolna — no summary
• bpm-ai-inference — Inference and server for local AI implementations of bpm-ai-core abstractions.
• byzerllm — ByzerLLM: Byzer LLM
• chatdocs — Chat with your documents offline using AI.
• 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.
• docuverse — State-of-the-art Retrieval/Search engine models, including ElasticSearch, ChromaDB, Milvus, and PrimeQA
• drugdetector — A simple wrapper to support drug detection in medical texts.
• easy-transformers — Utils for dealing with transformers
• eternalblue — A diarization package
• 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.
• fast-sentence-transformers — This repository contains code to run faster sentence-transformers. Simply, faster, sentence-transformers.
• fastnn — A python library and framework for fast neural network computations.
• fastrag — An Efficient Retrieval Augmentation and Generation Framework for Intel Hardware.
• finetuning-suite — A fine-tuning suite based on Transformers and LoRA.
• flying-delta-legacy — Interface between LLMs and your data
• fms-hf-tuning — FMS HF Tuning
• ft-suite — A fine-tuning suite based on Transformers and LoRA.
• gallama — An opinionated Llama Server engine with a focus on agentic tasks
• 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.
• glayout — A human language to analog layout API with support for different technologies.
• goldenretriever-core — Dense Retriever
• gptdb — GPT-DB 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.
• gptq-Quantizer — A Python package for GPTQ quantization
• green-bit-llm — A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.
• h2ogpt — no summary
• icortex — Jupyter kernel that can generate Python code from natural language prompts
• indic-eval — A package to make LLM evaluation easier
• infinity_emb — Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip.
• instructlab — CLI for interacting with InstructLab
• kozmoserver-huggingface — HuggingFace runtime for KozmoServer
• langport — A large language model serving platform.
• lazyllm-llamafactory — Easy-to-use LLM fine-tuning framework
• lexikos — A collection of pronunciation dictionaries and neural grapheme-to-phoneme models.
• lighteval — A lightweight and configurable evaluation package
• llama-index-embeddings-gaudi — llama-index embeddings gaudi integration
• 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-gaudi — llama-index llms gaudi integration
• llama-index-llms-openvino — llama-index llms openvino integration
• llama-index-llms-optimum-intel — llama-index llms optimum intel integration
• llama-index-multi-modal-llms-openvino — llama-index multi_modal_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 models. 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.
• llamafactory — Easy-to-use LLM fine-tuning framework
• llamafactory-songlab — Easy-to-use LLM fine-tuning framework
• 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 — An object-oriented wrapper around language models with caching, batching, and more.
• luis-v-subtitler — A Python package to use AI to subtitle any video in any language
• mase-tools — Machine-Learning Accelerator System Exploration Tools
• materials-spum-multi — Materials SPUM project.
• mlserver-huggingface — HuggingFace runtime for MLServer
• mlserver-huggingface-striveworks — HuggingFace runtime for MLServer
• mmda — MMDA - multimodal document analysis
• mt-researcher — MT Researcher is an autonomous agent designed for comprehensive online research on a variety of tasks.
• nendo-plugin-textgen — A text generation plugin using local LLMs or other text generation methods. Builds on top of `transformers` by Hugging Face.
• nexaai-metal — Nexa AI SDK
• oat-llm — Online AlignmenT (OAT) for LLMs.
• olive-ai — Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.
• openbb-chat — Deep learning package to add chat capabilities to OpenBB
• openrlhf — A Ray-based High-performance RLHF framework.
• 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-benchmark — Optimum-Benchmark is a unified multi-backend utility for benchmarking Transformers, Timm, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.
• 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 Trainium 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