Reflection-Tuning is a project focused on improving the quality of instruction-tuning data through a reflection-based method. It introduces Selective Reflection-Tuning, where the student model can decide whether to accept the improvements made by the teacher model. The project aims to generate high-quality instruction-response pairs by defining specific criteria for the oracle model to follow and respond to. It also evaluates the efficacy and relevance of instruction-response pairs using the r-IFD metric. The project provides code for reflection and selection processes, along with data and model weights for both V1 and V2 methods.

This is the official repository for 'Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing'. Magpie is a tool designed to synthesize high-quality instruction data at scale by extracting it directly from an aligned Large Language Models (LLMs). It aims to democratize AI by generating large-scale alignment data and enhancing the transparency of model alignment processes. Magpie has been tested on various model families and can be used to fine-tune models for improved performance on alignment benchmarks such as AlpacaEval, ArenaHard, and WildBench.

BABILong is a generative benchmark designed to evaluate the performance of NLP models in processing long documents with distributed facts. It consists of 20 tasks that simulate interactions between characters and objects in various locations, requiring models to distinguish important information from irrelevant details. The tasks vary in complexity and reasoning aspects, with test samples potentially containing millions of tokens. The benchmark aims to challenge and assess the capabilities of Large Language Models (LLMs) in handling complex, long-context information.

MME-RealWorld is a benchmark designed to address real-world applications with practical relevance, featuring 13,366 high-resolution images and 29,429 annotations across 43 tasks. It aims to provide substantial recognition challenges and overcome common barriers in existing Multimodal Large Language Model benchmarks, such as small data scale, restricted data quality, and insufficient task difficulty. The dataset offers advantages in data scale, data quality, task difficulty, and real-world utility compared to existing benchmarks. It also includes a Chinese version with additional images and QA pairs focused on Chinese scenarios.

MMStar is an elite vision-indispensable multi-modal benchmark comprising 1,500 challenge samples meticulously selected by humans. It addresses two key issues in current LLM evaluation: the unnecessary use of visual content in many samples and the existence of unintentional data leakage in LLM and LVLM training. MMStar evaluates 6 core capabilities across 18 detailed axes, ensuring a balanced distribution of samples across all dimensions.

STILL is an open-source project exploring slow-thinking reasoning systems, focusing on o1-like reasoning systems. The project has released technical reports on enhancing LLM reasoning with reward-guided tree search algorithms and implementing slow-thinking reasoning systems using an imitate, explore, and self-improve framework. The project aims to replicate the capabilities of industry-level reasoning systems by fine-tuning reasoning models with long-form thought data and iteratively refining training datasets.

OREAL is a reinforcement learning framework designed for mathematical reasoning tasks, aiming to achieve optimal performance through outcome reward-based learning. The framework utilizes behavior cloning, reshaping rewards, and token-level reward models to address challenges in sparse rewards and partial correctness. OREAL has achieved significant results, with a 7B model reaching 94.0 pass@1 accuracy on MATH-500 and surpassing previous 32B models. The tool provides training tutorials and Hugging Face model repositories for easy access and implementation.

K2 (GeoLLaMA) is a large language model for geoscience, trained on geoscience literature and fine-tuned with knowledge-intensive instruction data. It outperforms baseline models on objective and subjective tasks. The repository provides K2 weights, core data of GeoSignal, GeoBench benchmark, and code for further pretraining and instruction tuning. The model is available on Hugging Face for use. The project aims to create larger and more powerful geoscience language models in the future.

MathCoder is a repository focused on enhancing mathematical reasoning by fine-tuning open-source language models to use code for modeling and deriving math equations. It introduces MathCodeInstruct dataset with solutions interleaving natural language, code, and execution results. The repository provides MathCoder models capable of generating code-based solutions for challenging math problems, achieving state-of-the-art scores on MATH and GSM8K datasets. It offers tools for model deployment, inference, and evaluation, along with a citation for referencing the work.

This repository contains code for training reward models for Deep Reinforcement Learning-based Reward-modulated Hierarchical Fine-tuning (DRL-based RLHF), Iterative Selection Fine-tuning (Rejection sampling fine-tuning), and iterative Decision Policy Optimization (DPO). The reward models are trained using a Bradley-Terry model based on the Gemma and Mistral language models. The resulting reward models achieve state-of-the-art performance on the RewardBench leaderboard for reward models with base models of up to 13B parameters.

The repository Adaptive-MT-LLM-Fine-tuning contains code and data for the paper 'Fine-tuning Large Language Models for Adaptive Machine Translation'. It focuses on enhancing Mistral 7B, a large language model, for real-time adaptive machine translation in the medical domain. The fine-tuning process involves using zero-shot and one-shot translation prompts to improve terminology and style adherence. The repository includes training and test data, data processing code, fuzzy match retrieval techniques, fine-tuning methods, conversion to CTranslate2 format, tokenizers, translation codes, and evaluation metrics.

MInference is a tool designed to accelerate pre-filling for long-context Language Models (LLMs) by leveraging dynamic sparse attention. It achieves up to a 10x speedup for pre-filling on an A100 while maintaining accuracy. The tool supports various decoding LLMs, including LLaMA-style models and Phi models, and provides custom kernels for attention computation. MInference is useful for researchers and developers working with large-scale language models who aim to improve efficiency without compromising accuracy.

FuseMedML is a Python framework designed to accelerate machine learning-based discovery in the medical field by promoting code reuse. It provides a flexible design concept where data is stored in a nested dictionary, allowing easy handling of multi-modality information. The framework includes components for creating custom models, loss functions, metrics, and data processing operators. Additionally, FuseMedML offers 'batteries included' key components such as fuse.data for data processing, fuse.eval for model evaluation, and fuse.dl for reusable deep learning components. It supports PyTorch and PyTorch Lightning libraries and encourages the creation of domain extensions for specific medical domains.

LongBench v2 is a benchmark designed to assess the ability of large language models (LLMs) to handle long-context problems requiring deep understanding and reasoning across various real-world multitasks. It consists of 503 challenging multiple-choice questions with contexts ranging from 8k to 2M words, covering six major task categories. The dataset is collected from nearly 100 highly educated individuals with diverse professional backgrounds and is designed to be challenging even for human experts. The evaluation results highlight the importance of enhanced reasoning ability and scaling inference-time compute to tackle the long-context challenges in LongBench v2.

AgentCPM is a series of open-source LLM agents jointly developed by THUNLP, Renmin University of China, ModelBest, and the OpenBMB community. It addresses challenges faced by agents in real-world applications such as limited long-horizon capability, autonomy, and generalization. The team focuses on building deep research capabilities for agents, releasing AgentCPM-Explore, a deep-search LLM agent, and AgentCPM-Report, a deep-research LLM agent. AgentCPM-Explore is the first open-source agent model with 4B parameters to appear on widely used long-horizon agent benchmarks. AgentCPM-Report is built on the 8B-parameter base model MiniCPM4.1, autonomously generating long-form reports with extreme performance and minimal footprint, designed for high-privacy scenarios with offline and agile local deployment.

GEPA (Genetic-Pareto) is a framework for optimizing arbitrary systems composed of text components like AI prompts, code snippets, or textual specs against any evaluation metric. It employs LLMs to reflect on system behavior, using feedback from execution and evaluation traces to drive targeted improvements. Through iterative mutation, reflection, and Pareto-aware candidate selection, GEPA evolves robust, high-performing variants with minimal evaluations, co-evolving multiple components in modular systems for domain-specific gains. The repository provides the official implementation of the GEPA algorithm as proposed in the paper titled 'GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning'.

Reflection-Tuning is a project focused on improving the quality of instruction-tuning data through a reflection-based method. It introduces Selective Reflection-Tuning, where the student model can decide whether to accept the improvements made by the teacher model. The project aims to generate high-quality instruction-response pairs by defining specific criteria for the oracle model to follow and respond to. It also evaluates the efficacy and relevance of instruction-response pairs using the r-IFD metric. The project provides code for reflection and selection processes, along with data and model weights for both V1 and V2 methods.

Prometheus-Eval is a repository dedicated to evaluating large language models (LLMs) in generation tasks. It provides state-of-the-art language models like Prometheus 2 (7B & 8x7B) for assessing in pairwise ranking formats and achieving high correlation scores with benchmarks. The repository includes tools for training, evaluating, and using these models, along with scripts for fine-tuning on custom datasets. Prometheus aims to address issues like fairness, controllability, and affordability in evaluations by simulating human judgments and proprietary LM-based assessments.

LLMs is a Chinese large language model technology stack for practical use. It includes high-availability pre-training, SFT, and DPO preference alignment code framework. The repository covers pre-training data cleaning, high-concurrency framework, SFT dataset cleaning, data quality improvement, and security alignment work for Chinese large language models. It also provides open-source SFT dataset construction, pre-training from scratch, and various tools and frameworks for data cleaning, quality optimization, and task alignment.

ProX is a lm-based data refinement framework that automates the process of cleaning and improving data used in pre-training large language models. It offers better performance, domain flexibility, efficiency, and cost-effectiveness compared to traditional methods. The framework has been shown to improve model performance by over 2% and boost accuracy by up to 20% in tasks like math. ProX is designed to refine data at scale without the need for manual adjustments, making it a valuable tool for data preprocessing in natural language processing tasks.

Autonomous agents are designed to achieve specific objectives through self-guided instructions. With the emergence and growth of large language models (LLMs), there is a growing trend in utilizing LLMs as fundamental controllers for these autonomous agents. This repository conducts a comprehensive survey study on the construction, application, and evaluation of LLM-based autonomous agents. It explores essential components of AI agents, application domains in natural sciences, social sciences, and engineering, and evaluation strategies. The survey aims to be a resource for researchers and practitioners in this rapidly evolving field.

AI Product Home is a repository dedicated to collecting various AI commercial or open-source products. It provides assistance in submitting issues, self-recommendation, correcting resources, and more. The repository also features AI tools like Build Naidia, Autopod, Rytr, Mubert, and a virtual town driven by AI. It includes sections for AI models, chat dialogues, AI assistants, code assistance, artistic creation, content creation, and more. The repository covers a wide range of AI-related tools and resources for users interested in AI products and services.

AI-Catalog is a curated list of AI tools, platforms, and resources across various domains. It serves as a comprehensive repository for users to discover and explore a wide range of AI applications. The catalog includes tools for tasks such as text-to-image generation, summarization, prompt generation, writing assistance, code assistance, developer tools, low code/no code tools, audio editing, video generation, 3D modeling, search engines, chatbots, email assistants, fun tools, gaming, music generation, presentation tools, website builders, education assistants, autonomous AI agents, photo editing, AI extensions, deep face/deep fake detection, text-to-speech, startup tools, SQL-related AI tools, education tools, and text-to-video conversion.

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.

The AI Bootcamp is a comprehensive training program focusing on real-world applications to equip individuals with the skills and knowledge needed to excel as AI engineers. The bootcamp covers topics such as Real-World PyTorch, Machine Learning Projects, Fine-tuning Tiny LLM, Deployment of LLM to Production, AI Agents with GPT-4 Turbo, CrewAI, Llama 3, and more. Participants will learn foundational skills in Python for AI, ML Pipelines, Large Language Models (LLMs), AI Agents, and work on projects like RagBase for private document chat.

EasyAi is a lightweight, beginner-friendly Java artificial intelligence algorithm framework. It can be seamlessly integrated into Java projects with Maven, requiring no additional environment configuration or dependencies. The framework provides pre-packaged modules for image object detection and AI customer service, as well as various low-level algorithm tools for deep learning, machine learning, reinforcement learning, heuristic learning, and matrix operations. Developers can easily develop custom micro-models tailored to their business needs.

Awesome AI Newsletters is a curated list of AI-related newsletters that provide the latest news, trends, tools, and insights in the field of Artificial Intelligence. It includes a variety of newsletters covering general AI news, prompts for marketing and productivity, AI job opportunities, and newsletters tailored for professionals in the AI industry. Whether you are a beginner looking to stay updated on AI advancements or a professional seeking to enhance your knowledge and skills, this repository offers a collection of valuable resources to help you navigate the world of AI.

Reflection-Tuning is a project focused on improving the quality of instruction-tuning data through a reflection-based method. It introduces Selective Reflection-Tuning, where the student model can decide whether to accept the improvements made by the teacher model. The project aims to generate high-quality instruction-response pairs by defining specific criteria for the oracle model to follow and respond to. It also evaluates the efficacy and relevance of instruction-response pairs using the r-IFD metric. The project provides code for reflection and selection processes, along with data and model weights for both V1 and V2 methods.