Reverse Dependencies of deepspeed

The following projects have a declared dependency on deepspeed:

• accelerate — Accelerate
• adapter-transformers — A friendly fork of HuggingFace's Transformers, adding Adapters to PyTorch language models
• aeiva — aeiva is a general AI agent framework
• aesthetic-predictor-v2-5 — Aesthetic predictor v2.5
• agilerl — AgileRL is a deep reinforcement learning library focused on improving RL development through RLOps.
• aimet-onnx — AIMET onnx package
• aistrainer — AI Specialization Trainer for LLM models
• aivoifu — Easy and fast AI Waifu voice generation
• alexa-teacher-models — Alexa Teacher Models
• alignment-handbook — The Alignment Handbook
• alpaca-farm — no summary
• alphadev — AlphaDev - Pytorch
• alphafold3-pytorch-lightning-hydra — AlphaFold 3 - Pytorch
• Andromeda-llm — andromeda - Pytorch
• andromeda-torch — Andromeda - Pytorch
• archai — Platform for Neural Architecture Search
• arctic-training — Snowflake LLM training library
• ASRChild — Package for ASRChild
• autobiasdetector — tools for detecting bias patterns of LLMs
• axolotl — LLM Trainer
• badam — Package which implements the algorithm proposed by "BAdam: A Memory Efficient Full Parameter Training Method for Large Language Models".
• catalyst — Catalyst. Accelerated deep learning R&D with PyTorch.
• catalyst-pdm — Catalyst fork compatible with PDM
• chatllama-py — no summary
• cm3 — Description of the cm3 package
• codegeex — CodeGeeX: A Open Multilingual Code Generation Model.
• codemmlu — CodeMMLU Evaluator: A framework for evaluating language models on CodeMMLU benchmark.
• cody-adapter-transformers — A friendly fork of HuggingFace's Transformers, adding Adapters to PyTorch language models
• collie-lm — CoLLiE: Collaborative Training of Large Language Models in an Efficient Way
• cut-cross-entropy — Code for cut cross entropy, a memory efficient implementation of linear-cross-entropy loss.
• danoliterate — Benchmark of Generative Large Language Models in Danish
• dbgpt-hub — DB-GPT-Hub: Text-to-SQL parsing with LLMs
• deepspeed-mii — deepspeed mii
• factory-sdk — factory SDK
• fair-esm — Evolutionary Scale Modeling (esm): Pretrained language models for proteins. From Facebook AI Research.
• fate-llm — Federated Learning for Large Language Models
• fedml — A research and production integrated edge-cloud library for federated/distributed machine learning at anywhere at any scale.
• fm-optimized-inference — no summary
• fmcore — A specialized toolkit for scaling experimental research with Foundation Models.
• formless — Handwritten + image OCR.
• gigagan — GigaGAN - Scaling up GANs for Text-to-Image Synthesis
• gpt3-torch — GPT3 - Pytorch
• gpt4-torch — GPT4 - Pytorch
• inspiremusic — InspireMusic: A Fundamental Music, Song and Audio Generation Framework and Toolkits
• instructlab-training — Training Library
• kogitune — The Kogitune 🦊 LLM Project
• kosmos-2 — kosmos-2 - Pytorch
• lazyllm — A Low-code Development Tool For Building Multi-agent LLMs Applications.
• lazyllm-beta — A Low-code Development Tool For Building Multi-agent LLMs Applications.
• lazyllm-llamafactory — Easy-to-use LLM fine-tuning framework
• lbster — Language models for Biological Sequence Transformation and Evolutionary Representation.
• Lightning — The Deep Learning framework to train, deploy, and ship AI products Lightning fast.
• lightning-fabric — no summary
• lightning-gpt — GPT training in Lightning
• lightning-lite — no summary
• lightning-transformers — Lightning Transformers.
• llamafactory — Unified Efficient Fine-Tuning of 100+ LLMs
• llamafactory-songlab — Easy-to-use LLM fine-tuning framework
• llava-torch — Towards GPT-4 like large language and visual assistant.
• llavaction — LLaVAction: Evaluating and Training Multi-Modal Large Language Models for Action Recognition
• 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-optimized-inference — no summary
• llm-serve — An LLM inference solution to quickly deploy productive LLM service
• llmtuner — Easy-to-use LLM fine-tuning framework
• lmflow-benchmark — LMFlow: Large Model Flow.
• lmflow-deploy — LMFlow: Large Model Flow.
• lmflow-diffusion — LMFlow: Large Model Flow.
• lmflow-eval — LMFlow: Large Model Flow.
• lmflow-evaluate — LMFlow: Large Model Flow.
• lmflow-evaluator — LMFlow: Large Model Flow.
• lmflow-finetune — LMFlow: Large Model Flow.
• lmflow-finetuner — LMFlow: Large Model Flow.
• lmflow-inference — LMFlow: Large Model Flow.
• lmflow-inferencer — LMFlow: Large Model Flow.
• lmflow-pretrain — LMFlow: Large Model Flow.
• lmflow-pretrainer — LMFlow: Large Model Flow.
• lmflow-vision — LMFlow: Large Model Flow.
• manifest-ml — Manifest for Prompting Foundation Models.
• mantis-vl — Official Codes for of "MANTIS: Interleaved Multi-Image Instruction Tuning"
• mase-tools — Machine-Learning Accelerator System Exploration Tools
• mask2former — Mask2Former
• megaladon — Megaladon - Pytorch
• memorag — A Python package for memory-augmented retrieval-augmented generation
• mengzi-zero-shot — NLU & NLG (zero-shot) depend on mengzi-t5-base-mt
• metatreelib — PyTorch Implementation for MetaTree: Learning a Decision Tree Algorithm with Transformers
• mw-adapter-transformers — A friendly fork of HuggingFace's Transformers, adding Adapters to PyTorch language models
• narration-xtts2 — Projeto que baseado em um json cria narrações frase a frase em uma lista de frases, com flexibilidade de parametros do modelo XTTS2
• nn-gpt — LLM-Based Neural Network Generator
• oat-llm — Online AlignmenT (OAT) for LLMs.
• ochat — An efficient framework for training and serving top-tier, open-source conversational LLMs.
• oh-my-bloom — 中文BLOOM语言模型
• OmniEvent — A tookit for event extraction.
• OpenMind — openMind is a magicain who takes you to experience the mystery and creativity of AI.
• openrlhf — A Ray-based High-performance RLHF framework.
• 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.
• otter-ai — Otter: A Multi-Modal Model with In-Context Instruction Tuning
• pandora-llm — Red-teaming large language models for train data leakage
• phi-torch — Phi - Pytorch
• Protenix — A trainable PyTorch reproduction of AlphaFold 3.
• py-data-juicer — A One-Stop Data Processing System for Large Language Models.