Best AI tools for< Evaluate Performance >

Langtrace AI is an open-source observability tool powered by Scale3 Labs that helps monitor, evaluate, and improve LLM (Large Language Model) applications. It collects and analyzes traces and metrics to provide insights into the ML pipeline, ensuring security through SOC 2 Type II certification. Langtrace supports popular LLMs, frameworks, and vector databases, offering end-to-end observability and the ability to build and deploy AI applications with confidence.

GeniusReview is a 360° AI-powered performance review tool that helps users save time by providing tailored answers to performance review questions. Users can input employee names and roles to customize the review process, rank skills, add questions, and generate reviews with a selected tone. The tool aims to streamline the performance review process and enhance feedback quality for various roles in organizations.

FinetuneDB is an AI fine-tuning platform that allows users to easily create and manage datasets to fine-tune LLMs, evaluate outputs, and iterate on production data. It integrates with open-source and proprietary foundation models, and provides a collaborative editor for building datasets. FinetuneDB also offers a variety of features for evaluating model performance, including human and AI feedback, automated evaluations, and model metrics tracking.

MonitUp is an AI-powered time tracking software that helps you track computer activity, gain insights into work habits, and boost productivity. It uses artificial intelligence to generate personalized suggestions to help you increase productivity and work more efficiently. MonitUp also offers a performance appraisal feature for remote employees, allowing you to evaluate and improve their performance based on objective data.

Betterworks is an intelligent performance management platform that simplifies performance management, fosters greater manager effectiveness, higher employee engagement, and intelligent decision-making for HR leaders and organizations. It offers features such as AI for HR analytics & insights, integrations, accessibility, security, and manager effectiveness. Betterworks is designed to help organizations align their workforce around strategic priorities, drive collaboration, and continuously improve performance.

Confident AI is an open-source evaluation infrastructure for Large Language Models (LLMs). It provides a centralized platform to judge LLM applications, ensuring substantial benefits and addressing any weaknesses in LLM implementation. With Confident AI, companies can define ground truths to ensure their LLM is behaving as expected, evaluate performance against expected outputs to pinpoint areas for iterations, and utilize advanced diff tracking to guide towards the optimal LLM stack. The platform offers comprehensive analytics to identify areas of focus and features such as A/B testing, evaluation, output classification, reporting dashboard, dataset generation, and detailed monitoring to help productionize LLMs with confidence.

IndieZebra is a tool designed to help users A/B test different variations of their Product Hunt launch page, enabling them to drive higher engagement and conversions. By allowing users to test taglines and descriptions with different personas, IndieZebra provides valuable insights into audience engagement. The tool aims to help users stand out from the competition and reach their maximum potential by identifying the best performing copy for their product launch on Product Hunt.

LlamaIndex is a leading data framework designed for building LLM (Large Language Model) applications. It allows enterprises to turn their data into production-ready applications by providing functionalities such as loading data from various sources, indexing data, orchestrating workflows, and evaluating application performance. The platform offers extensive documentation, community-contributed resources, and integration options to support developers in creating innovative LLM applications.

CloudExam AI is an online testing platform developed by Hanke Numerical Union Technology Co., Ltd. It provides stable and efficient AI online testing services, including intelligent grouping, intelligent monitoring, and intelligent evaluation. The platform ensures test fairness by implementing automatic monitoring level regulations and three random strategies. It prioritizes information security by combining software and hardware to secure data and identity. With global cloud deployment and flexible architecture, it supports hundreds of thousands of concurrent users. CloudExam AI offers features like queue interviews, interactive pen testing, data-driven cockpit, AI grouping, AI monitoring, AI evaluation, random question generation, dual-seat testing, facial recognition, real-time recording, abnormal behavior detection, test pledge book, student information verification, photo uploading for answers, inspection system, device detection, scoring template, ranking of results, SMS/email reminders, screen sharing, student fees, and collaboration with selected schools.

Teammately is an AI tool that redefines how Human AI-Engineers build AI. It is an Agentic AI for AI development process, designed to enable Human AI-Engineers to focus on more creative and productive missions in AI development. Teammately follows the best practices of Human LLM DevOps and offers features like Development Prompt Engineering, Knowledge Tuning, Evaluation, and Optimization to assist in the AI development process. The tool aims to revolutionize AI engineering by allowing AI AI-Engineers to handle technical tasks, while Human AI-Engineers focus on planning and aligning AI with human preferences and requirements.

Encord is a leading data development platform designed for computer vision and multimodal AI teams. It offers a comprehensive suite of tools to manage, clean, and curate data, streamline labeling and workflow management, and evaluate AI model performance. With features like data indexing, annotation, and active model evaluation, Encord empowers users to accelerate their AI data workflows and build robust models efficiently.

SQOR is a plug-n-play AI tool designed for C-Level Executives to make stress-free decision-making in business intelligence. It provides a zero-code BI solution, offering KPIs at your fingertips without the need for expert knowledge. The platform enables users to access and share business intelligence data from various SaaS tools, facilitating collaboration and informed decision-making across the organization. SQOR's unique Execution Score Algorithm evaluates execution health at different levels, ensuring stakeholders are empowered with actionable insights.

Valuemetrix is an AI-enhanced investment analysis platform designed for investors seeking to redefine their investment journey. The platform offers cutting-edge AI technology, institutional-level data, and expert analysis to provide users with well-informed investment decisions. Valuemetrix empowers users to elevate their investment experience through AI-driven insights, real-time market news, stock reports, market analysis, and tailored financial information for over 100,000 international publicly traded companies.

Insidr AI is a real-time analysis tool that helps users track their competition by providing actionable insights about products. Powered by Supervised AI, the tool offers features such as analyzing user reviews, gaining insights on competitors, and performing various analyses like sentiment analysis, SWOT analysis, and trend analysis. Users can also transcribe recordings, perform KPI analysis, and find competitive edges. With a focus on providing accurate data and insights, Insidr AI aims to help businesses make informed decisions and stay ahead of the competition.

Encord is a complete data development platform designed for AI applications, specifically tailored for computer vision and multimodal AI teams. It offers tools to intelligently manage, clean, and curate data, streamline labeling and workflow management, and evaluate model performance. Encord aims to unlock the potential of AI for organizations by simplifying data-centric AI pipelines, enabling the building of better models and deploying high-quality production AI faster.

Arize AI is an AI Observability & LLM Evaluation Platform that helps you monitor, troubleshoot, and evaluate your machine learning models. With Arize, you can catch model issues, troubleshoot root causes, and continuously improve performance. Arize is used by top AI companies to surface, resolve, and improve their models.

BenchLLM is an AI tool designed for AI engineers to evaluate LLM-powered apps by running and evaluating models with a powerful CLI. It allows users to build test suites, choose evaluation strategies, and generate quality reports. The tool supports OpenAI, Langchain, and other APIs out of the box, offering automation, visualization of reports, and monitoring of model performance.

Weavel is an AI tool designed to revolutionize prompt engineering for large language models (LLMs). It offers features such as tracing, dataset curation, batch testing, and evaluations to enhance the performance of LLM applications. Weavel enables users to continuously optimize prompts using real-world data, prevent performance regression with CI/CD integration, and engage in human-in-the-loop interactions for scoring and feedback. Ape, the AI prompt engineer, outperforms competitors on benchmark tests and ensures seamless integration and continuous improvement specific to each user's use case. With Weavel, users can effortlessly evaluate LLM applications without the need for pre-existing datasets, streamlining the assessment process and enhancing overall performance.

ThinkTask is a project and team management tool that utilizes ChatGPT's capabilities to enhance productivity and streamline task management. It offers AI-generated reports and insights, AI usage tracking, Team Pulse for visualizing task types and status, Project Progress Table for monitoring project timelines and budgets, Task Insights for illustrating task interdependencies, and a comprehensive Overview for visualizing progress and managing dependencies. Additionally, ThinkTask features one-click auto-task creation with notes from ChatGPT, auto-tagging for task organization, and AI-suggested task assignments based on past experience and skills. It provides a unified workspace for notes, tasks, databases, collaboration, and customization.

RevSure is an AI-powered platform designed for high-growth marketing teams to optimize marketing ROI and attribution. It offers full-funnel attribution, deep funnel optimization, predictive insights, and campaign performance tracking. The platform integrates with various data sources to provide unified funnel reporting and personalized recommendations for improving pipeline health and conversion rates. RevSure's AI engine powers features like campaign spend reallocation, next-best touch analysis, and journey timeline construction, enabling users to make data-driven decisions and accelerate revenue growth.

This repository contains code for building cooperative embodied agents modularly with large language models. The agents are trained to perform tasks in two different environments: ThreeDWorld Multi-Agent Transport (TDW-MAT) and Communicative Watch-And-Help (C-WAH). TDW-MAT is a multi-agent environment where agents must transport objects to a goal position using containers. C-WAH is an extension of the Watch-And-Help challenge, which enables agents to send messages to each other. The code in this repository can be used to train agents to perform tasks in both of these environments.

GPT4Point is a unified framework for point-language understanding and generation. It aligns 3D point clouds with language, providing a comprehensive solution for tasks such as 3D captioning and controlled 3D generation. The project includes an automated point-language dataset annotation engine, a novel object-level point cloud benchmark, and a 3D multi-modality model. Users can train and evaluate models using the provided code and datasets, with a focus on improving models' understanding capabilities and facilitating the generation of 3D objects.

The ASReview project implements active learning for systematic reviews, utilizing AI-aided pipelines to assist in finding relevant texts for search tasks. It accelerates the screening of textual data with minimal human input, saving time and increasing output quality. The software offers three modes: Oracle for interactive screening, Exploration for teaching purposes, and Simulation for evaluating active learning models. ASReview LAB is designed to support decision-making in any discipline or industry by improving efficiency and transparency in screening large amounts of textual data.

Groma is a grounded multimodal assistant that excels in region understanding and visual grounding. It can process user-defined region inputs and generate contextually grounded long-form responses. The tool presents a unique paradigm for multimodal large language models, focusing on visual tokenization for localization. Groma achieves state-of-the-art performance in referring expression comprehension benchmarks. The tool provides pretrained model weights and instructions for data preparation, training, inference, and evaluation. Users can customize training by starting from intermediate checkpoints. Groma is designed to handle tasks related to detection pretraining, alignment pretraining, instruction finetuning, instruction following, and more.

Amber is the first model in the LLM360 family, an initiative for comprehensive and fully open-sourced LLMs. It is a 7B English language model with the LLaMA architecture. The model type is a language model with the same architecture as LLaMA-7B. It is licensed under Apache 2.0. The resources available include training code, data preparation, metrics, and fully processed Amber pretraining data. The model has been trained on various datasets like Arxiv, Book, C4, Refined-Web, StarCoder, StackExchange, and Wikipedia. The hyperparameters include a total of 6.7B parameters, hidden size of 4096, intermediate size of 11008, 32 attention heads, 32 hidden layers, RMSNorm ε of 1e^-6, max sequence length of 2048, and a vocabulary size of 32000.

The KAN-GPT repository is a PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling. It provides a model for generating text based on prompts, with a focus on improving performance compared to traditional MLP-GPT models. The repository includes scripts for training the model, downloading datasets, and evaluating model performance. Development tasks include integrating with other libraries, testing, and documentation.

LLM-SFT is a Chinese large model fine-tuning tool that supports models such as ChatGLM, LlaMA, Bloom, Baichuan-7B, and frameworks like LoRA, QLoRA, DeepSpeed, UI, and TensorboardX. It facilitates tasks like fine-tuning, inference, evaluation, and API integration. The tool provides pre-trained weights for various models and datasets for Chinese language processing. It requires specific versions of libraries like transformers and torch for different functionalities.

Zshot is a highly customizable framework for performing Zero and Few shot named entity and relationships recognition. It can be used for mentions extraction, wikification, zero and few shot named entity recognition, zero and few shot named relationship recognition, and visualization of zero-shot NER and RE extraction. The framework consists of two main components: the mentions extractor and the linker. There are multiple mentions extractors and linkers available, each serving a specific purpose. Zshot also includes a relations extractor and a knowledge extractor for extracting relations among entities and performing entity classification. The tool requires Python 3.6+ and dependencies like spacy, torch, transformers, evaluate, and datasets for evaluation over datasets like OntoNotes. Optional dependencies include flair and blink for additional functionalities. Zshot provides examples, tutorials, and evaluation methods to assess the performance of the components.

RLAIF-V is a novel framework that aligns MLLMs in a fully open-source paradigm for super GPT-4V trustworthiness. It maximally exploits open-source feedback from high-quality feedback data and online feedback learning algorithm. Notable features include achieving super GPT-4V trustworthiness in both generative and discriminative tasks, using high-quality generalizable feedback data to reduce hallucination of different MLLMs, and exhibiting better learning efficiency and higher performance through iterative alignment.

This repository contains code for the paper 'Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models'. It focuses on fine-tuning CLIP in an unsupervised manner to enhance its robustness against visual adversarial attacks. By replacing the vision encoder of large vision-language models with the fine-tuned CLIP models, it achieves state-of-the-art adversarial robustness on various vision-language tasks. The repository provides adversarially fine-tuned ViT-L/14 CLIP models and offers insights into zero-shot classification settings and clean accuracy improvements.

ABigSurveyOfLLMs is a repository that compiles surveys on Large Language Models (LLMs) to provide a comprehensive overview of the field. It includes surveys on various aspects of LLMs such as transformers, alignment, prompt learning, data management, evaluation, societal issues, safety, misinformation, attributes of LLMs, efficient LLMs, learning methods for LLMs, multimodal LLMs, knowledge-based LLMs, extension of LLMs, LLMs applications, and more. The repository aims to help individuals quickly understand the advancements and challenges in the field of LLMs through a collection of recent surveys and research papers.

Wandbot is a question-answering bot designed for Weights & Biases documentation. It employs Retrieval Augmented Generation with a ChromaDB backend for efficient responses. The bot features periodic data ingestion, integration with Discord and Slack, and performance monitoring through logging. It has a fallback mechanism for model selection and is evaluated based on retrieval accuracy and model-generated responses. The implementation includes creating document embeddings, constructing the Q&A RAGPipeline, model selection, deployment on FastAPI, Discord, and Slack, logging and analysis with Weights & Biases Tables, and performance evaluation.

Bonito is an open-source model for conditional task generation, converting unannotated text into task-specific training datasets for instruction tuning. It is a lightweight library built on top of Hugging Face `transformers` and `vllm` libraries. The tool supports various task types such as question answering, paraphrase generation, sentiment analysis, summarization, and more. Users can easily generate synthetic instruction tuning datasets using Bonito for zero-shot task adaptation.

Step-DPO is a method for enhancing long-chain reasoning ability of LLMs with a data construction pipeline creating a high-quality dataset. It significantly improves performance on math and GSM8K tasks with minimal data and training steps. The tool fine-tunes pre-trained models like Qwen2-7B-Instruct with Step-DPO, achieving superior results compared to other models. It provides scripts for training, evaluation, and deployment, along with examples and acknowledgements.

RouteLLM is a framework for serving and evaluating LLM routers. It allows users to launch an OpenAI-compatible API that routes requests to the best model based on cost thresholds. Trained routers are provided to reduce costs while maintaining performance. Users can easily extend the framework, compare router performance, and calibrate cost thresholds. RouteLLM supports multiple routing strategies and benchmarks, offering a lightweight server and evaluation framework. It enables users to evaluate routers on benchmarks, calibrate thresholds, and modify model pairs. Contributions for adding new routers and benchmarks are welcome.

Merlin is a groundbreaking model capable of generating natural language responses intricately linked with object trajectories of multiple images. It excels in predicting and reasoning about future events based on initial observations, showcasing unprecedented capability in future prediction and reasoning. Merlin achieves state-of-the-art performance on the Future Reasoning Benchmark and multiple existing multimodal language models benchmarks, demonstrating powerful multi-modal general ability and foresight minds.

RAG-Retrieval provides full-chain RAG retrieval fine-tuning and inference code. It supports fine-tuning any open-source RAG retrieval models, including vector (embedding, graph a), delayed interactive models (ColBERT, graph d), interactive models (cross encoder, graph c). For inference, RAG-Retrieval focuses on ranking (reranker) and has developed a lightweight Python library rag-retrieval, providing a unified way to call any different RAG ranking models.

The GraphRAG project is a data pipeline and transformation suite designed to extract meaningful, structured data from unstructured text using LLMs. It enhances LLMs' ability to reason about private data. The repository provides guidance on using knowledge graph memory structures to enhance LLM outputs, with a warning about the potential costs of GraphRAG indexing. It offers contribution guidelines, development resources, and encourages prompt tuning for optimal results. The Responsible AI FAQ addresses GraphRAG's capabilities, intended uses, evaluation metrics, limitations, and operational factors for effective and responsible use.

YGO Agent is a project focused on using deep learning to master the Yu-Gi-Oh! trading card game. It utilizes reinforcement learning and large language models to develop advanced AI agents that aim to surpass human expert play. The project provides a platform for researchers and players to explore AI in complex, strategic game environments.

LL3DA is a Large Language 3D Assistant that responds to both visual and textual interactions within complex 3D environments. It aims to help Large Multimodal Models (LMM) comprehend, reason, and plan in diverse 3D scenes by directly taking point cloud input and responding to textual instructions and visual prompts. LL3DA achieves remarkable results in 3D Dense Captioning and 3D Question Answering, surpassing various 3D vision-language models. The code is fully released, allowing users to train customized models and work with pre-trained weights. The tool supports training with different LLM backends and provides scripts for tuning and evaluating models on various tasks.

A curated list of open source repositories for AI Engineers. The repository provides a comprehensive collection of tools and frameworks for various AI-related tasks such as AI Gateway, AI Workload Manager, Copilot Development, Dataset Engineering, Evaluation, Fine Tuning, Function Calling, Graph RAG, Guardrails, Local Model Inference, LLM Agent Framework, Model Serving, Observability, Pre Training, Prompt Engineering, RAG Framework, Security, Structured Extraction, Structured Generation, Vector DB, and Voice Agent.

LLM-Pruner is a tool for structural pruning of large language models, allowing task-agnostic compression while retaining multi-task solving ability. It supports automatic structural pruning of various LLMs with minimal human effort. The tool is efficient, requiring only 3 minutes for pruning and 3 hours for post-training. Supported LLMs include Llama-3.1, Llama-3, Llama-2, LLaMA, BLOOM, Vicuna, and Baichuan. Updates include support for new LLMs like GQA and BLOOM, as well as fine-tuning results achieving high accuracy. The tool provides step-by-step instructions for pruning, post-training, and evaluation, along with a Gradio interface for text generation. Limitations include issues with generating repetitive or nonsensical tokens in compressed models and manual operations for certain models.

EasyLM is a one-stop solution for pre-training, fine-tuning, evaluating, and serving large language models in JAX/Flax. It simplifies the process by leveraging JAX's pjit functionality to scale up training to multiple TPU/GPU accelerators. Built on top of Huggingface's transformers and datasets, EasyLM offers an easy-to-use and customizable codebase for training large language models without the complexity found in other frameworks. It supports sharding model weights and training data across multiple accelerators, enabling multi-TPU/GPU training on a single host or across multiple hosts on Google Cloud TPU Pods. EasyLM currently supports models like LLaMA, LLaMA 2, and LLaMA 3.

Simplifine is an open-source library designed for easy LLM finetuning, enabling users to perform tasks such as supervised fine tuning, question-answer finetuning, contrastive loss for embedding tasks, multi-label classification finetuning, and more. It provides features like WandB logging, in-built evaluation tools, automated finetuning parameters, and state-of-the-art optimization techniques. The library offers bug fixes, new features, and documentation updates in its latest version. Users can install Simplifine via pip or directly from GitHub. The project welcomes contributors and provides comprehensive documentation and support for users.

LLM Hallucination Index - RAG Special is a comprehensive evaluation of large language models (LLMs) focusing on context length and open vs. closed-source attributes. The index explores the impact of context length on model performance and tests the assumption that closed-source LLMs outperform open-source ones. It also investigates the effectiveness of prompting techniques like Chain-of-Note across different context lengths. The evaluation includes 22 models from various brands, analyzing major trends and declaring overall winners based on short, medium, and long context insights. Methodologies involve rigorous testing with different context lengths and prompting techniques to assess models' abilities in handling extensive texts and detecting hallucinations.

FATE-LLM is a framework supporting federated learning for large and small language models. It promotes training efficiency of federated LLMs using Parameter-Efficient methods, protects the IP of LLMs using FedIPR, and ensures data privacy during training and inference through privacy-preserving mechanisms.

This repository is a curated list of open-source libraries for production large language models. It includes tools for data preprocessing, training/finetuning, evaluation/benchmarking, serving/inference, application/RAG, testing/monitoring, and guardrails/security. The repository also provides a new category called LLM Cookbook/Examples for showcasing examples and guides on using various LLM APIs.

This repository contains code for grounding large language models' knowledge in BabyAI-Text using the GLAM method. It includes the BabyAI-Text environment, code for experiments, and training agents. The repository is structured with folders for the environment, experiments, agents, configurations, SLURM scripts, and training scripts. Installation steps involve creating a conda environment, installing PyTorch, required packages, BabyAI-Text, and Lamorel. The launch process involves using Lamorel with configs and training scripts. Users can train a language model and evaluate performance on test episodes using provided scripts and config entries.

This repository contains a sophisticated deterministic graph-based solution for answering complex questions using a controllable autonomous agent. The solution is designed to ensure that answers are solely based on the provided data, avoiding hallucinations. It involves various steps such as PDF loading, text preprocessing, summarization, database creation, encoding, and utilizing large language models. The algorithm follows a detailed workflow involving planning, retrieval, answering, replanning, content distillation, and performance evaluation. Heuristics and techniques implemented focus on content encoding, anonymizing questions, task breakdown, content distillation, chain of thought answering, verification, and model performance evaluation.

DeepPavlov is an open-source conversational AI library built on PyTorch. It is designed for the development of production-ready chatbots and complex conversational systems, as well as for research in the area of NLP and dialog systems. The library offers a wide range of models for tasks such as Named Entity Recognition, Intent/Sentence Classification, Question Answering, Sentence Similarity/Ranking, Syntactic Parsing, and more. DeepPavlov also provides embeddings like BERT, ELMo, and FastText for various languages, along with AutoML capabilities and integrations with REST API, Socket API, and Amazon AWS.

CRAB is a framework for building LLM agent benchmark environments in a Python-centric way. It is cross-platform and multi-environment, allowing the creation of agent environments supporting various deployment options. The framework offers easy-to-use configuration with the ability to add new actions and define environments seamlessly. CRAB also provides a novel benchmarking suite with tasks and evaluators defined in Python, along with a unique graph evaluator method for detailed metrics.

The Multipack sampler is a tool designed for padding-free distributed training of large language models. It optimizes batch processing efficiency using an approximate solution to the identical machine scheduling problem. The V2 update further enhances the packing algorithm complexity, achieving better throughput for a large number of nodes. It includes two variants for models with different attention types, aiming to balance sequence lengths and optimize packing efficiency. Users can refer to the provided benchmark for evaluating efficiency, utilization, and L^2 lag. The tool is compatible with PyTorch DataLoader and is released under the MIT license.

FedLLM-Bench is a realistic benchmark for the Federated Learning of Large Language Models community. It includes datasets for federated instruction tuning and preference alignment tasks, exhibiting diversities in language, quality, quantity, instruction, sequence length, embedding, and preference. The repository provides training scripts and code for open-ended evaluation, aiming to facilitate research and development in federated learning of large language models.

CALF (LLaTA) is a cross-modal fine-tuning framework that bridges the distribution discrepancy between temporal data and the textual nature of LLMs. It introduces three cross-modal fine-tuning techniques: Cross-Modal Match Module, Feature Regularization Loss, and Output Consistency Loss. The framework aligns time series and textual inputs, ensures effective weight updates, and maintains consistent semantic context for time series data. CALF provides scripts for long-term and short-term forecasting, requires Python 3.9, and utilizes word token embeddings for model training.

Eagle is a family of Vision-Centric High-Resolution Multimodal LLMs that enhance multimodal LLM perception using a mix of vision encoders and various input resolutions. The model features a channel-concatenation-based fusion for vision experts with different architectures and knowledge, supporting up to over 1K input resolution. It excels in resolution-sensitive tasks like optical character recognition and document understanding.

AICIty-reID 2020 is a repository containing the 1st Place submission to AICity Challenge 2020 re-id track by Baidu-UTS. It includes models trained on Paddlepaddle and Pytorch, with performance metrics and trained models provided. Users can extract features, perform camera and direction prediction, and access related repositories for drone-based building re-id, vehicle re-ID, person re-ID baseline, and person/vehicle generation. Citations are also provided for research purposes.

TriForce is a training-free tool designed to accelerate long sequence generation. It supports long-context Llama models and offers both on-chip and offloading capabilities. Users can achieve a 2.2x speedup on a single A100 GPU. TriForce also provides options for offloading with tensor parallelism or without it, catering to different hardware configurations. The tool includes a baseline for comparison and is optimized for performance on RTX 4090 GPUs. Users can cite the associated paper if they find TriForce useful for their projects.

GuideLLM is a powerful tool for evaluating and optimizing the deployment of large language models (LLMs). By simulating real-world inference workloads, GuideLLM helps users gauge the performance, resource needs, and cost implications of deploying LLMs on various hardware configurations. This approach ensures efficient, scalable, and cost-effective LLM inference serving while maintaining high service quality. Key features include performance evaluation, resource optimization, cost estimation, and scalability testing.

WebLINX is a Python library and dataset for real-world website navigation with multi-turn dialogue. The repository provides code for training models reported in the WebLINX paper, along with a comprehensive API to work with the dataset. It includes modules for data processing, model evaluation, and utility functions. The modeling directory contains code for processing, training, and evaluating models such as DMR, LLaMA, MindAct, Pix2Act, and Flan-T5. Users can install specific dependencies for HTML processing, video processing, model evaluation, and library development. The evaluation module provides metrics and functions for evaluating models, with ongoing work to improve documentation and functionality.

AutoWebGLM is a project focused on developing a language model-driven automated web navigation agent. It extends the capabilities of the ChatGLM3-6B model to navigate the web more efficiently and address real-world browsing challenges. The project includes features such as an HTML simplification algorithm, hybrid human-AI training, reinforcement learning, rejection sampling, and a bilingual web navigation benchmark for testing AI web navigation agents.

ABQ-LLM is a novel arbitrary bit quantization scheme that achieves excellent performance under various quantization settings while enabling efficient arbitrary bit computation at the inference level. The algorithm supports precise weight-only quantization and weight-activation quantization. It provides pre-trained model weights and a set of out-of-the-box quantization operators for arbitrary bit model inference in modern architectures.

RAGHub is a community-driven project focused on cataloging new and emerging frameworks, projects, and resources in the Retrieval-Augmented Generation (RAG) ecosystem. It aims to help users stay ahead of changes in the field by providing a platform for the latest innovations in RAG. The repository includes information on RAG frameworks, evaluation frameworks, optimization frameworks, citation frameworks, engines, search reranker frameworks, projects, resources, and real-world use cases across industries and professions.

NineRec is a benchmark dataset suite for evaluating transferable recommendation models. It provides datasets for pre-training and transfer learning in recommender systems, focusing on multimodal and foundation model tasks. The dataset includes user-item interactions, item texts in multiple languages, item URLs, and raw images. Researchers can use NineRec to develop more effective and efficient methods for pre-training recommendation models beyond end-to-end training. The dataset is accompanied by code for dataset preparation, training, and testing in PyTorch environment.

FastFit is a Python package designed for fast and accurate few-shot classification, especially for scenarios with many semantically similar classes. It utilizes a novel approach integrating batch contrastive learning and token-level similarity score, significantly improving multi-class classification performance in speed and accuracy across various datasets. FastFit provides a convenient command-line tool for training text classification models with customizable parameters. It offers a 3-20x improvement in training speed, completing training in just a few seconds. Users can also train models with Python scripts and perform inference using pretrained models for text classification tasks.

Fira is a memory-efficient training framework for Large Language Models (LLMs) that enables full-rank training under low-rank constraint. It introduces a method for training with full-rank gradients of full-rank weights, achieved with just two lines of equations. The framework includes pre-training and fine-tuning functionalities, packaged as a Python library for easy use. Fira utilizes Adam optimizer by default and provides options for weight decay. It supports pre-training LLaMA models on the C4 dataset and fine-tuning LLaMA-7B models on commonsense reasoning tasks.

Advanced tool for crafting impactful employee reviews.

Simply write any topic (anything superheroes, vacuums, Pokémon’, diamonds…) and I’ll provide the evaluation criteria you can use.

深度解析财务报告，提供专业洞察

Analyzes AFL draft data to evaluate clubs' historical performance

AI-powered sports analytics expert for sportsmind.io users.

Expert on ESG topics, providing detailed, up-to-date, and structured answers.

Company Profile Builder and Analyzer

Your assistant for coaching youth sports teams.

Guides organizational effectiveness via team-focused strategies and learning.

Technical and informative discussions on drilling and its applications.

Experto en FIFA, proporciona consejos de estrategia y análisis de juego.

Analyzes markets, offers predictions on commodities, crypto, and companies.

你是一共拥有最前沿的知识储备，丰富的教学经验，优秀的课程设计能力的优秀教育工作者。

I simulate tough Customer Support scenarios for Agent Training.

Does Pool Performance of Elite Triathletes Predict Open-Water Performance?

Enhances organizational performance through strategic skills development initiatives.

Enhances organizational performance through employee learning and development initiatives.

Helps you evaluate whether or not tech platforms match UNESCO's Internet for Trust Guidelines for the Governance of Digital Platforms

Guides leadership growth to enhance organizational performance.

Designs effective training materials to enhance organizational learning and performance.