tiny-llm-zh
从零实现一个小参数量中文大语言模型。
Stars: 147
Tiny LLM zh is a project aimed at building a small-parameter Chinese language large model for quick entry into learning large model-related knowledge. The project implements a two-stage training process for large models and subsequent human alignment, including tokenization, pre-training, instruction fine-tuning, human alignment, evaluation, and deployment. It is deployed on ModeScope Tiny LLM website and features open access to all data and code, including pre-training data and tokenizer. The project trains a tokenizer using 10GB of Chinese encyclopedia text to build a Tiny LLM vocabulary. It supports training with Transformers deepspeed, multiple machine and card support, and Zero optimization techniques. The project has three main branches: llama2_torch, main tiny_llm, and tiny_llm_moe, each with specific modifications and features.
README:
本项目旨在构建一个小参数量的中文语言大模型，用于快速入门学习大模型相关知识，如果此项目对你有用，可以点一下start，谢谢！
模型架构：整体模型架构采用开源通用架构，包括：RMSNorm，RoPE，MHA等
实现细节：实现大模型两阶段训练及后续人类对齐，即：分词(Tokenizer) -> 预训练(PTM) -> 指令微调(SFT) -> 人类对齐(RLHF, DPO) -> 测评 -> 量化 -> 部署。
项目已部署，可以在如下网站上体验。
项目特点：
- 公开全部数据及代码，包括预训练数据，tokenizer等；（Tiny LLM Datasets）
- 走通大模型整个流程：分词(Tokenizer) -> 预训练(PTM) -> 指令微调(SFT) -> 人类对齐(RLHF, DPO) -> 测评 -> 部署；
- 公开预训练token 42B，SFT数据400w条，RL数据 17w条；
- 训练 Tokenizer：10G 中文百科文本训练 20K 中文词表，与 Llama2 词表合并，构建Tiny LLM词表；
- 使用 Transformers deepspeed 进行训练，支持多机多卡，支持 Zero 等优化技术；
- 所有代码
Bash脚本启动，支持不同大小的模型，如16m, 42m, 92m, 210m, 440m等； - 支持 MoE 架构，在 tiny_llm_moe 支持最新共享专家，平衡专家等技术；
- 支持 vLLM 推理框架；
- 支持 llama.cpp 推理框架；
本项目主要有三个分支，推荐学习 主分支，具体区别如下：
- llama2_torch ： 模型架构采用原版 Llama2 架构，只是将部分的输入输出修改为适合训练的格式；
-
maintiny_llm： 对齐开源社区模型，使用Transformers库构建底层模型，也使用Transformers库进行多卡多机训练； -
tiny_llm_moe ： 在
tiny_llm的基础上，修改MLP层为MoE模型，使用Transformers库进行多卡多机训练。
注意：
- 因资源限制，本项目的第一要务是走通大模型整个流程，而不是调教比较好的效果，故评测结果分数较低，部分生成错误。
- 详细的数据处理，训练过程见
doc文件夹（正在整理。。。）
模型已托管在 Huggingface 和 ModeScope 中，可运行代码自动下载。
建议使用 Huggingface 在线加载模型，如果运行不了，在试 ModeScope ；如果需要本地运行，修改model_id中的路径为本地目录，即可运行。
- python 3.8 and above
- pytorch 2.0 and above
- transformers 4.37.2 and above
- CUDA 11.4 and above are recommended. (if training)
pip install -r requirements.txt from transformers import AutoTokenizer, AutoModelForCausalLM
from transformers.generation import GenerationConfig
model_id = "wdndev/tiny_llm_sft_92m"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True)
generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True)
sys_text = "你是由wdndev开发的个人助手。"
# user_text = "世界上最大的动物是什么？"
# user_text = "介绍一下刘德华。"
user_text = "介绍一下中国。"
input_txt = "\n".join(["<|system|>", sys_text.strip(),
"<|user|>", user_text.strip(),
"<|assistant|>"]).strip() + "\n"
generation_config.max_new_tokens = 200
model_inputs = tokenizer(input_txt, return_tensors="pt").to(model.device)
generated_ids = model.generate(model_inputs.input_ids, generation_config=generation_config)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)from modelscope import AutoModelForCausalLM, AutoTokenizer
model_id = "wdndev/tiny_llm_sft_92m"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True)
sys_text = "你是由wdndev开发的个人助手。"
# user_text = "世界上最大的动物是什么？"
# user_text = "介绍一下刘德华。"
user_text = "介绍一下中国。"
input_txt = "\n".join(["<|system|>", sys_text.strip(),
"<|user|>", user_text.strip(),
"<|assistant|>"]).strip() + "\n"
model_inputs = tokenizer(input_txt, return_tensors="pt").to(model.device)
generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=200)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)生成效果
问：世界上最大的动物是什么？
答：目前已知最大的动物是蓝鲸（Balaenoptera musculus），这是一个庞大的哺乳动物，属于须鲸亚目、须鲸科中的最大物种。蓝鲸的身长可达30米以上，体重可达175吨。它们在海洋中生活，主要以浮游生物为食，如甲壳类动物和小型鱼类等。由于其巨大的体型和复杂的生态群落，蓝鲸成为海洋旅游的热门景点之一。
问：介绍一下刘德华。
答：刘德华是一位香港流行歌手、演员和导演，他在音乐界的贡献非常巨大。他是华语乐坛历史上最伟大的艺人之一，代表作品包括《爱我身体》和《肥皂泡》。他也经常参演电影和电视剧，并在电视上受到好评。
问：介绍一下中国。
答：中国是位于东亚的大陆，被欧洲以及亚洲和其他大陆所包围。它是中国第二大文明和世界上最大的经济体之一。中国的历史可以追溯到公元前5000年左右，从古至今都有其独特的文化和语言传承者。
LLM分词器的构建方式有两种：一种是自己构造词表，训练一个分词器；另一种是选择开源模型训练好的分词器。
本项目为了方便，从优秀的开源项目中选择词表，考虑到训练的模型较小，且词表大小影响模型大小，故优先选择词表较小的开源项目；经过比较，最终选择 ChatGLM3 的词表，该词表大小为 64798 。
自己构造词表方式见 tokenizer，扩充 LLaMA2的32K词表为50K，增加20K中文词表，详细扩充方式见文档或tokenizer/README.md.
注意：本项目使用的ChatGLM3的词表。
模型结构采用类Llama2的结构，具体包括：RMSNorm，RoPE，MHA等；
具体参数细节如下所示：
| model | hidden size | intermediate size | n_layers | n_heads | max context length | params | vocab size |
|---|---|---|---|---|---|---|---|
| tiny-llm-16m | 120 | 384 | 6 | 6 | 512 | 16M | 64798 |
| tiny-llm-42m | 288 | 768 | 6 | 6 | 512 | 42M | 64798 |
| tiny-llm-92m | 512 | 1024 | 8 | 8 | 1024 | 92M | 64798 |
| tiny-llm-210m | 768 | 2048 | 16 | 12 | 1024 | 210M | 64798 |
| tiny-llm-440m | 1024 | 2816 | 24 | 16 | 1024 | 440M | 64798 |
| tiny-llm-1_5b | 2048 | 5504 | 24 | 16 | 1024 | 1.5B | 64798 |
因训练数据和微调数据，大部分都是中文数据，所以在C-Eval和CMMLU这两个数据集上进行模型的评估；使用OpenCompass工具，进行模型评估，评估分数如下所示：
| model | Type | C-Eval | CMMLU |
|---|---|---|---|
| tiny-llm-92m | Base | 23.48 | 25.02 |
| tiny-llm-92m | Chat | 26.79 | 26.59 |
Base模型，采用评测方式 ppl 方式进行评测；Chat模型，采用 gen 方式评测。具体区别如下图所示：
注意：只对常用的两个模型进行了评测，分数较低，其余模型评测意义不大。
网页Demo已部署，可以在如下网站上体验：ModeScope Tiny LLM
如果想在本地运行网页Demo，注意修改 web_demo.py 文件中模型的路径model_id，输入如下命令即可运行：
streamlit run web_demo.py
Transfomers 框架部署，位于 demo/infer_chat.py 和 demo/infer_func.py 文件中，和其他LLM运行无太大区别，注意输入的拼接即可。
详细vllm部署见 vllm
如果使用CUDA 12 以上和PyTorch 2.1 以上，可以直接使用以下命令安装vLLM。
pip install vllm==0.4.0否则请参考vLLM官方的安装说明。
安装完成后，还需要以下操作~
- 把
vllm/tinyllm.py文件复制到env环境对应的vllm/model_executor/models目录下。 - 然后在vllm/model_executor/models/__init__.py文件增加一行代码
"TinyllmForCausalLM": ("tinyllm", "TinyllmForCausalLM"),由于模型结构是自己定义的，vllm官方未实现，需要自己手动加入
详细 llama.cpp 部署见 llama.cpp
Tiny LLM 92M 模型已支持 llama.cpp C++ 推理框架，建议在 linux 环境下测试，windows效果不好；
所支持 llama.cpp 为自己修改的版本，仓库链接为： llama.cpp.tinyllm
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for tiny-llm-zh
Similar Open Source Tools
tiny-llm-zh
Tiny LLM zh is a project aimed at building a small-parameter Chinese language large model for quick entry into learning large model-related knowledge. The project implements a two-stage training process for large models and subsequent human alignment, including tokenization, pre-training, instruction fine-tuning, human alignment, evaluation, and deployment. It is deployed on ModeScope Tiny LLM website and features open access to all data and code, including pre-training data and tokenizer. The project trains a tokenizer using 10GB of Chinese encyclopedia text to build a Tiny LLM vocabulary. It supports training with Transformers deepspeed, multiple machine and card support, and Zero optimization techniques. The project has three main branches: llama2_torch, main tiny_llm, and tiny_llm_moe, each with specific modifications and features.
unsloth
Unsloth is a tool that allows users to fine-tune large language models (LLMs) 2-5x faster with 80% less memory. It is a free and open-source tool that can be used to fine-tune LLMs such as Gemma, Mistral, Llama 2-5, TinyLlama, and CodeLlama 34b. Unsloth supports 4-bit and 16-bit QLoRA / LoRA fine-tuning via bitsandbytes. It also supports DPO (Direct Preference Optimization), PPO, and Reward Modelling. Unsloth is compatible with Hugging Face's TRL, Trainer, Seq2SeqTrainer, and Pytorch code. It is also compatible with NVIDIA GPUs since 2018+ (minimum CUDA Capability 7.0).
Chinese-Mixtral-8x7B
Chinese-Mixtral-8x7B is an open-source project based on Mistral's Mixtral-8x7B model for incremental pre-training of Chinese vocabulary, aiming to advance research on MoE models in the Chinese natural language processing community. The expanded vocabulary significantly improves the model's encoding and decoding efficiency for Chinese, and the model is pre-trained incrementally on a large-scale open-source corpus, enabling it with powerful Chinese generation and comprehension capabilities. The project includes a large model with expanded Chinese vocabulary and incremental pre-training code.
litellm
LiteLLM is a tool that allows you to call all LLM APIs using the OpenAI format. This includes Bedrock, Huggingface, VertexAI, TogetherAI, Azure, OpenAI, and more. LiteLLM manages translating inputs to provider's `completion`, `embedding`, and `image_generation` endpoints, providing consistent output, and retry/fallback logic across multiple deployments. It also supports setting budgets and rate limits per project, api key, and model.
build_MiniLLM_from_scratch
This repository aims to build a low-parameter LLM model through pretraining, fine-tuning, model rewarding, and reinforcement learning stages to create a chat model capable of simple conversation tasks. It features using the bert4torch training framework, seamless integration with transformers package for inference, optimized file reading during training to reduce memory usage, providing complete training logs for reproducibility, and the ability to customize robot attributes. The chat model supports multi-turn conversations. The trained model currently only supports basic chat functionality due to limitations in corpus size, model scale, SFT corpus size, and quality.
west
WeST is a Speech Recognition/Transcript tool developed in 300 lines of code, inspired by SLAM-ASR and LLaMA 3.1. The model includes a Language Model (LLM), a Speech Encoder, and a trainable Projector. It requires training data in jsonl format with 'wav' and 'txt' entries. WeST can be used for training and decoding speech recognition models.
InternVL
InternVL scales up the ViT to _**6B parameters**_ and aligns it with LLM. It is a vision-language foundation model that can perform various tasks, including: **Visual Perception** - Linear-Probe Image Classification - Semantic Segmentation - Zero-Shot Image Classification - Multilingual Zero-Shot Image Classification - Zero-Shot Video Classification **Cross-Modal Retrieval** - English Zero-Shot Image-Text Retrieval - Chinese Zero-Shot Image-Text Retrieval - Multilingual Zero-Shot Image-Text Retrieval on XTD **Multimodal Dialogue** - Zero-Shot Image Captioning - Multimodal Benchmarks with Frozen LLM - Multimodal Benchmarks with Trainable LLM - Tiny LVLM InternVL has been shown to achieve state-of-the-art results on a variety of benchmarks. For example, on the MMMU image classification benchmark, InternVL achieves a top-1 accuracy of 51.6%, which is higher than GPT-4V and Gemini Pro. On the DocVQA question answering benchmark, InternVL achieves a score of 82.2%, which is also higher than GPT-4V and Gemini Pro. InternVL is open-sourced and available on Hugging Face. It can be used for a variety of applications, including image classification, object detection, semantic segmentation, image captioning, and question answering.
gollama
Gollama is a tool designed for managing Ollama models through a Text User Interface (TUI). Users can list, inspect, delete, copy, and push Ollama models, as well as link them to LM Studio. The application offers interactive model selection, sorting by various criteria, and actions using hotkeys. It provides features like sorting and filtering capabilities, displaying model metadata, model linking, copying, pushing, and more. Gollama aims to be user-friendly and useful for managing models, especially for cleaning up old models.
api-for-open-llm
This project provides a unified backend interface for open large language models (LLMs), offering a consistent experience with OpenAI's ChatGPT API. It supports various open-source LLMs, enabling developers to seamlessly integrate them into their applications. The interface features streaming responses, text embedding capabilities, and support for LangChain, a tool for developing LLM-based applications. By modifying environment variables, developers can easily use open-source models as alternatives to ChatGPT, providing a cost-effective and customizable solution for various use cases.
Muice-Chatbot
Muice-Chatbot is an AI chatbot designed to proactively engage in conversations with users. It is based on the ChatGLM2-6B and Qwen-7B models, with a training dataset of 1.8K+ dialogues. The chatbot has a speaking style similar to a 2D girl, being somewhat tsundere but willing to share daily life details and greet users differently every day. It provides various functionalities, including initiating chats and offering 5 available commands. The project supports model loading through different methods and provides onebot service support for QQ users. Users can interact with the chatbot by running the main.py file in the project directory.
Llama-Chinese
Llama中文社区是一个专注于Llama模型在中文方面的优化和上层建设的高级技术社区。 **已经基于大规模中文数据，从预训练开始对Llama2模型进行中文能力的持续迭代升级【Done】**。**正在对Llama3模型进行中文能力的持续迭代升级【Doing】** 我们热忱欢迎对大模型LLM充满热情的开发者和研究者加入我们的行列。
video-subtitle-remover
Video-subtitle-remover (VSR) is a software based on AI technology that removes hard subtitles from videos. It achieves the following functions: - Lossless resolution: Remove hard subtitles from videos, generate files with subtitles removed - Fill the region of removed subtitles using a powerful AI algorithm model (non-adjacent pixel filling and mosaic removal) - Support custom subtitle positions, only remove subtitles in defined positions (input position) - Support automatic removal of all text in the entire video (no input position required) - Support batch removal of watermark text from multiple images.
Langchain-Chatchat
LangChain-Chatchat is an open-source, offline-deployable retrieval-enhanced generation (RAG) large model knowledge base project based on large language models such as ChatGLM and application frameworks such as Langchain. It aims to establish a knowledge base Q&A solution that is friendly to Chinese scenarios, supports open-source models, and can run offline.
wenda
Wenda is a platform for large-scale language model invocation designed to efficiently generate content for specific environments, considering the limitations of personal and small business computing resources, as well as knowledge security and privacy issues. The platform integrates capabilities such as knowledge base integration, multiple large language models for offline deployment, auto scripts for additional functionality, and other practical capabilities like conversation history management and multi-user simultaneous usage.
SakuraLLM
SakuraLLM is a project focused on building large language models for Japanese to Chinese translation in the light novel and galgame domain. The models are based on open-source large models and are pre-trained and fine-tuned on general Japanese corpora and specific domains. The project aims to provide high-performance language models for galgame/light novel translation that are comparable to GPT3.5 and can be used offline. It also offers an API backend for running the models, compatible with the OpenAI API format. The project is experimental, with version 0.9 showing improvements in style, fluency, and accuracy over GPT-3.5.
chatluna
Chatluna is a machine learning model plugin that provides chat services with large language models. It is highly extensible, supports multiple output formats, and offers features like custom conversation presets, rate limiting, and context awareness. Users can deploy Chatluna under Koishi without additional configuration. The plugin supports various models/platforms like OpenAI, Azure OpenAI, Google Gemini, and more. It also provides preset customization using YAML files and allows for easy forking and development within Koishi projects. However, the project lacks web UI, HTTP server, and project documentation, inviting contributions from the community.
For similar tasks
vllm
vLLM is a fast and easy-to-use library for LLM inference and serving. It is designed to be efficient, flexible, and easy to use. vLLM can be used to serve a variety of LLM models, including Hugging Face models. It supports a variety of decoding algorithms, including parallel sampling, beam search, and more. vLLM also supports tensor parallelism for distributed inference and streaming outputs. It is open-source and available on GitHub.
bce-qianfan-sdk
The Qianfan SDK provides best practices for large model toolchains, allowing AI workflows and AI-native applications to access the Qianfan large model platform elegantly and conveniently. The core capabilities of the SDK include three parts: large model reasoning, large model training, and general and extension: * `Large model reasoning`: Implements interface encapsulation for reasoning of Yuyan (ERNIE-Bot) series, open source large models, etc., supporting dialogue, completion, Embedding, etc. * `Large model training`: Based on platform capabilities, it supports end-to-end large model training process, including training data, fine-tuning/pre-training, and model services. * `General and extension`: General capabilities include common AI development tools such as Prompt/Debug/Client. The extension capability is based on the characteristics of Qianfan to adapt to common middleware frameworks.
dstack
Dstack is an open-source orchestration engine for running AI workloads in any cloud. It supports a wide range of cloud providers (such as AWS, GCP, Azure, Lambda, TensorDock, Vast.ai, CUDO, RunPod, etc.) as well as on-premises infrastructure. With Dstack, you can easily set up and manage dev environments, tasks, services, and pools for your AI workloads.
tiny-llm-zh
Tiny LLM zh is a project aimed at building a small-parameter Chinese language large model for quick entry into learning large model-related knowledge. The project implements a two-stage training process for large models and subsequent human alignment, including tokenization, pre-training, instruction fine-tuning, human alignment, evaluation, and deployment. It is deployed on ModeScope Tiny LLM website and features open access to all data and code, including pre-training data and tokenizer. The project trains a tokenizer using 10GB of Chinese encyclopedia text to build a Tiny LLM vocabulary. It supports training with Transformers deepspeed, multiple machine and card support, and Zero optimization techniques. The project has three main branches: llama2_torch, main tiny_llm, and tiny_llm_moe, each with specific modifications and features.
LLMBox
LLMBox is a comprehensive library designed for implementing Large Language Models (LLMs) with a focus on a unified training pipeline and comprehensive model evaluation. It serves as a one-stop solution for training and utilizing LLMs, offering flexibility and efficiency in both training and utilization stages. The library supports diverse training strategies, comprehensive datasets, tokenizer vocabulary merging, data construction strategies, parameter efficient fine-tuning, and efficient training methods. For utilization, LLMBox provides comprehensive evaluation on various datasets, in-context learning strategies, chain-of-thought evaluation, evaluation methods, prefix caching for faster inference, support for specific LLM models like vLLM and Flash Attention, and quantization options. The tool is suitable for researchers and developers working with LLMs for natural language processing tasks.
chess_llm_interpretability
This repository evaluates Large Language Models (LLMs) trained on PGN format chess games using linear probes. It assesses the LLMs' internal understanding of board state and their ability to estimate player skill levels. The repo provides tools to train, evaluate, and visualize linear probes on LLMs trained to play chess with PGN strings. Users can visualize the model's predictions, perform interventions on the model's internal board state, and analyze board state and player skill level accuracy across different LLMs. The experiments in the repo can be conducted with less than 1 GB of VRAM, and training probes on the 8 layer model takes about 10 minutes on an RTX 3050. The repo also includes scripts for performing board state interventions and skill interventions, along with useful links to open-source code, models, datasets, and pretrained models.
LESS
This repository contains the code for the paper 'LESS: Selecting Influential Data for Targeted Instruction Tuning'. The work proposes a data selection method to choose influential data for inducing a target capability. It includes steps for warmup training, building the gradient datastore, selecting data for a task, and training with the selected data. The repository provides tools for data preparation, data selection pipeline, and evaluation of the model trained on the selected data.
AI-Bootcamp
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.
For similar jobs
sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.
teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.
ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.
classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.
chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.
BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students
uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.
griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.