Reverse Dependencies of accelerate
The following projects have a declared dependency on accelerate:
- geniusrise-text — Text bolts for geniusrise
- geniusrise-vision — Huggingface bolts for geniusrise
- 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
- gigagan-pytorch — GigaGAN - Pytorch
- giger — CLI for Stable Diffusion tasks.
- givt-pytorch — A partial implementation of Generative Infinite Vocabulary Transformer (GIVT) from Google Deepmind, in PyTorch.
- glmtuner — Fine-tuning ChatGLM-6B with PEFT
- gpt-blazing — todo
- gpt3-torch — GPT3 - Pytorch
- gpt4-torch — GPT4 - Pytorch
- gptfast — Accelerate transformer inference by 6-8.5x. Native to Huggingface and PyTorch.
- gptneox20b — test for a gpt model
- gpts — Unix language driver for software 2.0
- gpu-fit-llm — Helps estimate the memory requirements for a model on a GPU.
- gradnorm-pytorch — GradNorm - Pytorch
- gradsflow — An open-source AutoML Library based on PyTorch
- grag — A simple package for implementing RAG
- graph-of-thoughts — Python package for Graph of Thoughts that enables solving elaborate problems with Large Language Models
- graphpatch — graphpatch is a library for activation patching on PyTorch neural network models.
- grazier — A tool for calling (and calling out to) large language models.
- green-bit-llm — A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.
- grimbert — no summary
- gritlm — GritLM
- gt4sd — Generative Toolkit for Scientific Discovery (GT4SD).
- gtaccelerate — Plugin to use accelerate with gravitorch
- guardrail-ml — Monitor LLMs with custom metrics to scale with confidence
- h2ogpt — no summary
- happytransformer — Happy Transformer makes it easy to fine-tune NLP Transformer models and use them for inference.
- hcpdiff — A universal Stable-Diffusion toolbox
- healthsageai — HealthSage AI LLMs, Healthcare genAI platform
- heliumos.bixi — An open platform for load large language model.
- helmet — no summary
- hezar — Hezar: The all-in-one AI library for Persian, supporting a wide variety of tasks and modalities!
- horde-engine — A wrapper around ComfyUI to allow use by AI Horde.
- hordelib — A thin wrapper around ComfyUI to allow use by AI Horde.
- hugginglens — no summary
- HuggingSimpleCuellar-lib — Una libreria simple para usar modelos de Huggingface
- huixiangdou — Overcoming Group Chat Scenarios with LLM-based Technical Assistance
- hurricore — A deep learning framework based on PyTorch and Accelerate.
- idr-accelerate — no summary
- if-dsl-gui-ai — For generating and playing IF games
- image-reward — ImageReward
- imagen-pytorch — Imagen - unprecedented photorealism × deep level of language understanding
- img2tags — Tag images
- indomain — no summary
- inpars — InPars
- inranker — no summary
- insanely-fast-whisper — An insanely fast whisper CLI
- inspect-ai — Framework for large language model evaluations
- instruct-qa — Empirical evaluation of retrieval-augmented instruction-following models.
- integral_deid — PHI taggging and redaction
- internet-ml — Internet-ML: Allowing ML 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
- IOPaint — Image inpainting, outpainting tool powered by SOTA AI Model
- ipex-llm — Large Language Model Develop Toolkit
- irisml-tasks-llava — Irisml adapter tasks for LLAVA models
- jac-nlp — no summary
- jailbreakbench — An Open Robustness Benchmark for Jailbreaking Language Models
- jigs — Jeff's Image Generating Scripts
- k-diffusion — Karras et al. (2022) diffusion models for PyTorch
- kani-vision — Kani extension for supporting vision-language models (VLMs). Comes with model-agnostic support for GPT-Vision and LLaVA.
- kerastorch — llm model process for pytorch
- kgc — Cold Start Construction of Knowledge Graph.
- kimchima — The collections of tools for ML model development.
- kogitune — The Kogitune 🦊 LLM Project
- konfuzio-sdk — Konfuzio Software Development Kit
- kornia — Open Source Differentiable Computer Vision Library for PyTorch
- kosmos-2 — kosmos-2 - Pytorch
- KosmosX — Transformers at zeta scales
- kronfluence — Influence Functions with (Eigenvalue-corrected) Kronecker-factored Approximate Curvature
- Kurdish2Image — Create Kurdish style images from Text Based On Stable Diffusion Model
- l2hmc — L2HMC algorithm for sampling in Lattice QCD
- lambdaprompt — A functional programming interface for building AI systems
- langanisa — A langchain, transformers, and attention_sinks wrapper for longform response generation.
- langchain-llm — langchain llm wrapper
- langchain-ray — LangChain leveraging Ray.
- langport — A large language model serving platform.
- languru — The general purpose LLM app stacks.
- latentscope — Quickly embed, project, cluster and explore a dataset.
- lavague — Selenium code generation from text instructions
- leptonai — Lepton AI Platform
- lighteval — A lightweight and configurable evaluation package
- lightning-transformers — Lightning Transformers.
- linktransformer — A friendly way to do link, aggregate, cluster and de-duplicate dataframes using large language models.
- liqfit — Flexible Few-shot learning tool.
- llama-index-embeddings-ipex-llm — llama-index embeddings ipex-llm integration
- llama-index-embeddings-itrex — llama-index embeddings Intel Extension for Transformers integration
- llama-index-extra-llm — Just a simple extension for LlamaIndex for better apply some llm such as DeepSeek.
- llama-index-packs-llama-guard-moderator — llama-index packs llama_guard_moderator integration
- llama-index-packs-zephyr-query-engine — llama-index packs zephyr_query_engine 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.
- llama-trainer — Llama trainer utility
- llama2-wrapper — Use llama2-wrapper as your local llama2 backend for Generative Agents / Apps
- llamagym — Fine-tune LLM agents with online reinforcement learning
- llamatune — Haven's Tuning Library for LLM finetuning
- llava-torch — Towards GPT-4 like large language and visual assistant.
- llm-blender — LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths and weaknesses of multiple open-source large language models (LLMs). LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
- llm-connect — LLM Connect API