AI tools for LongBench v2 vs LongBench ACL 2024 performance comparison
Related Tools:
ai-agent-papers
The AI Agents Papers repository provides a curated collection of papers focusing on AI agents, covering topics such as agent capabilities, applications, architectures, and presentations. It includes a variety of papers on ideation, decision making, long-horizon tasks, learning, memory-based agents, self-evolving agents, and more. The repository serves as a valuable resource for researchers and practitioners interested in AI agent technologies and advancements.
LongBench
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.
optillm
optillm is an OpenAI API compatible optimizing inference proxy implementing state-of-the-art techniques to enhance accuracy and performance of LLMs, focusing on reasoning over coding, logical, and mathematical queries. By leveraging additional compute at inference time, it surpasses frontier models across diverse tasks.
Awesome-LLMOps
Awesome-LLMOps is a curated list of the best LLMOps tools, providing a comprehensive collection of frameworks and tools for building, deploying, and managing large language models (LLMs) and AI agents. The repository includes a wide range of tools for tasks such as building multimodal AI agents, fine-tuning models, orchestrating applications, evaluating models, and serving models for inference. It covers various aspects of the machine learning operations (MLOps) lifecycle, from training to deployment and observability. The tools listed in this repository cater to the needs of developers, data scientists, and machine learning engineers working with large language models and AI applications.
long-llms-learning
A repository sharing the panorama of the methodology literature on Transformer architecture upgrades in Large Language Models for handling extensive context windows, with real-time updating the newest published works. It includes a survey on advancing Transformer architecture in long-context large language models, flash-ReRoPE implementation, latest news on data engineering, lightning attention, Kimi AI assistant, chatglm-6b-128k, gpt-4-turbo-preview, benchmarks like InfiniteBench and LongBench, long-LLMs-evals for evaluating methods for enhancing long-context capabilities, and LLMs-learning for learning technologies and applicated tasks about Large Language Models.
KVCache-Factory
KVCache-Factory is a unified framework for KV Cache compression of diverse models. It supports multi-GPUs inference with big LLMs and various attention implementations. The tool enables KV cache compression without Flash Attention v2, multi-GPU inference, and specific models like Mistral. It also provides functions for KV cache budget allocation and batch inference. The visualization tools help in understanding the attention patterns of models.
MHA2MLA
This repository contains the code for the paper 'Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs'. It provides tools for fine-tuning and evaluating Llama models, converting models between different frameworks, processing datasets, and performing specific model training tasks like Partial-RoPE Fine-Tuning and Multiple-Head Latent Attention Fine-Tuning. The repository also includes commands for model evaluation using Lighteval and LongBench, along with necessary environment setup instructions.
llm-action
This repository provides a comprehensive guide to large language models (LLMs), covering various aspects such as training, fine-tuning, compression, and applications. It includes detailed tutorials, code examples, and explanations of key concepts and techniques. The repository is maintained by Liguo Dong, an AI researcher and engineer with expertise in LLM research and development.
Chinese-LLaMA-Alpaca-3
Chinese-LLaMA-Alpaca-3 is a project based on Meta's latest release of the new generation open-source large model Llama-3. It is the third phase of the Chinese-LLaMA-Alpaca open-source large model series projects (Phase 1, Phase 2). This project open-sources the Chinese Llama-3 base model and the Chinese Llama-3-Instruct instruction fine-tuned large model. These models incrementally pre-train with a large amount of Chinese data on the basis of the original Llama-3 and further fine-tune using selected instruction data, enhancing Chinese basic semantics and instruction understanding capabilities. Compared to the second-generation related models, significant performance improvements have been achieved.
MemoryLLM
MemoryLLM is a large language model designed for self-updating capabilities. It offers pretrained models with different memory capacities and features, such as chat models. The repository provides training code, evaluation scripts, and datasets for custom experiments. MemoryLLM aims to enhance knowledge retention and performance on various natural language processing tasks.
Chinese-LLaMA-Alpaca-2
Chinese-LLaMA-Alpaca-2 is a large Chinese language model developed by Meta AI. It is based on the Llama-2 model and has been further trained on a large dataset of Chinese text. Chinese-LLaMA-Alpaca-2 can be used for a variety of natural language processing tasks, including text generation, question answering, and machine translation. Here are some of the key features of Chinese-LLaMA-Alpaca-2: * It is the largest Chinese language model ever trained, with 13 billion parameters. * It is trained on a massive dataset of Chinese text, including books, news articles, and social media posts. * It can be used for a variety of natural language processing tasks, including text generation, question answering, and machine translation. * It is open-source and available for anyone to use. Chinese-LLaMA-Alpaca-2 is a powerful tool that can be used to improve the performance of a wide range of natural language processing tasks. It is a valuable resource for researchers and developers working in the field of artificial intelligence.
LLMEvaluation
The LLMEvaluation repository is a comprehensive compendium of evaluation methods for Large Language Models (LLMs) and LLM-based systems. It aims to assist academics and industry professionals in creating effective evaluation suites tailored to their specific needs by reviewing industry practices for assessing LLMs and their applications. The repository covers a wide range of evaluation techniques, benchmarks, and studies related to LLMs, including areas such as embeddings, question answering, multi-turn dialogues, reasoning, multi-lingual tasks, ethical AI, biases, safe AI, code generation, summarization, software performance, agent LLM architectures, long text generation, graph understanding, and various unclassified tasks. It also includes evaluations for LLM systems in conversational systems, copilots, search and recommendation engines, task utility, and verticals like healthcare, law, science, financial, and others. The repository provides a wealth of resources for evaluating and understanding the capabilities of LLMs in different domains.
LongCite
LongCite is a tool that enables Large Language Models (LLMs) to generate fine-grained citations in long-context Question Answering (QA) scenarios. It provides models trained on GLM-4-9B and Meta-Llama-3.1-8B, supporting up to 128K context. Users can deploy LongCite chatbots, generate accurate responses, and obtain precise sentence-level citations. The tool includes components for model deployment, Coarse to Fine (CoF) pipeline for data construction, model training using LongCite-45k dataset, evaluation with LongBench-Cite benchmark, and citation generation.
KIVI
KIVI is a plug-and-play 2bit KV cache quantization algorithm optimizing memory usage by quantizing key cache per-channel and value cache per-token to 2bit. It enables LLMs to maintain quality while reducing memory usage, allowing larger batch sizes and increasing throughput in real LLM inference workloads.
InfLLM
InfLLM is a training-free memory-based method that unveils the intrinsic ability of LLMs to process streaming long sequences. It stores distant contexts into additional memory units and employs an efficient mechanism to lookup token-relevant units for attention computation. Thereby, InfLLM allows LLMs to efficiently process long sequences while maintaining the ability to capture long-distance dependencies. Without any training, InfLLM enables LLMs pre-trained on sequences of a few thousand tokens to achieve superior performance than competitive baselines continually training these LLMs on long sequences. Even when the sequence length is scaled to 1, 024K, InfLLM still effectively captures long-distance dependencies.
LongLoRA
LongLoRA is a tool for efficient fine-tuning of long-context large language models. It includes LongAlpaca data with long QA data collected and short QA sampled, models from 7B to 70B with context length from 8k to 100k, and support for GPTNeoX models. The tool supports supervised fine-tuning, context extension, and improved LoRA fine-tuning. It provides pre-trained weights, fine-tuning instructions, evaluation methods, local and online demos, streaming inference, and data generation via Pdf2text. LongLoRA is licensed under Apache License 2.0, while data and weights are under CC-BY-NC 4.0 License for research use only.
