tiny-llm-zh

从零实现一个小参数量中文大语言模型。

Stars: 147

Visit

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:

Tiny LLM zh

1.简介

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。

ModeScope Tiny LLM

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；
main tiny_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。。。）

2.快速开始

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。

依赖安装

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

🤗 HuggingFace

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)

🤖 ModeScope

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。

3.模型

3.1 Tokenizer

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。

3.2 模型结构

模型结构采用类Llama2的结构，具体包括：RMSNorm，RoPE，MHA等；

3.3 模型尺寸

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

3.4 模型评估

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：

来源：ppl和gen模式有什么区别

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。

4.模型部署

4.1 网页Demo

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

4.2 Transformers

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。

4.3 FastAPI

4.4 vllm

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

4.5 llama.cpp

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 tasks

generate text fine-tune model evaluate model deploy model train tokenizer

For Jobs:

data scientist machine learning engineer research scientist ai engineer nlp specialist

Alternative AI tools for tiny-llm-zh

Similar Open Source Tools

tiny-llm-zh

github

: 147

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.

github

: 635

DeepAI

DeepAI is a proxy server that enhances the interaction experience of large language models (LLMs) by integrating the 'thinking chain' process. It acts as an intermediary layer, receiving standard OpenAI API compatible requests, using independent 'thinking services' to generate reasoning processes, and then forwarding the enhanced requests to the LLM backend of your choice. This ensures that responses are not only generated by the LLM but also based on pre-inference analysis, resulting in more insightful and coherent answers. DeepAI supports seamless integration with applications designed for the OpenAI API, providing endpoints for '/v1/chat/completions' and '/v1/models', making it easy to integrate into existing applications. It offers features such as reasoning chain enhancement, flexible backend support, API key routing, weighted random selection, proxy support, comprehensive logging, and graceful shutdown.

github

: 121

WeClone

WeClone is a tool that fine-tunes large language models using WeChat chat records. It utilizes approximately 20,000 integrated and effective data points, resulting in somewhat satisfactory outcomes that are occasionally humorous. The tool's effectiveness largely depends on the quantity and quality of the chat data provided. It requires a minimum of 16GB of GPU memory for training using the default chatglm3-6b model with LoRA method. Users can also opt for other models and methods supported by LLAMA Factory, which consume less memory. The tool has specific hardware and software requirements, including Python, Torch, Transformers, Datasets, Accelerate, and other optional packages like CUDA and Deepspeed. The tool facilitates environment setup, data preparation, data preprocessing, model downloading, parameter configuration, model fine-tuning, and inference through a browser demo or API service. Additionally, it offers the ability to deploy a WeChat chatbot, although users should be cautious due to the risk of account suspension by WeChat.

github

: 368

Steel-LLM

Steel-LLM is a project to pre-train a large Chinese language model from scratch using over 1T of data to achieve a parameter size of around 1B, similar to TinyLlama. The project aims to share the entire process including data collection, data processing, pre-training framework selection, model design, and open-source all the code. The goal is to enable reproducibility of the work even with limited resources. The name 'Steel' is inspired by a band '万能青年旅店' and signifies the desire to create a strong model despite limited conditions. The project involves continuous data collection of various cultural elements, trivia, lyrics, niche literature, and personal secrets to train the LLM. The ultimate aim is to fill the model with diverse data and leave room for individual input, fostering collaboration among users.

github

: 560

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.

github

: 2.7k

LLM-TPU

LLM-TPU project aims to deploy various open-source generative AI models on the BM1684X chip, with a focus on LLM. Models are converted to bmodel using TPU-MLIR compiler and deployed to PCIe or SoC environments using C++ code. The project has deployed various open-source models such as Baichuan2-7B, ChatGLM3-6B, CodeFuse-7B, DeepSeek-6.7B, Falcon-40B, Phi-3-mini-4k, Qwen-7B, Qwen-14B, Qwen-72B, Qwen1.5-0.5B, Qwen1.5-1.8B, Llama2-7B, Llama2-13B, LWM-Text-Chat, Mistral-7B-Instruct, Stable Diffusion, Stable Diffusion XL, WizardCoder-15B, Yi-6B-chat, Yi-34B-chat. Detailed model deployment information can be found in the 'models' subdirectory of the project. For demonstrations, users can follow the 'Quick Start' section. For inquiries about the chip, users can contact SOPHGO via the official website.

github

: 238

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.

github

: 4.0k

app-builder

AppBuilder SDK is a one-stop development tool for AI native applications, providing basic cloud resources, AI capability engine, Qianfan large model, and related capability components to improve the development efficiency of AI native applications.

github

: 553

Qwen-TensorRT-LLM

Qwen-TensorRT-LLM is a project developed for the NVIDIA TensorRT Hackathon 2023, focusing on accelerating inference for the Qwen-7B-Chat model using TRT-LLM. The project offers various functionalities such as FP16/BF16 support, INT8 and INT4 quantization options, Tensor Parallel for multi-GPU parallelism, web demo setup with gradio, Triton API deployment for maximum throughput/concurrency, fastapi integration for openai requests, CLI interaction, and langchain support. It supports models like qwen2, qwen, and qwen-vl for both base and chat models. The project also provides tutorials on Bilibili and blogs for adapting Qwen models in NVIDIA TensorRT-LLM, along with hardware requirements and quick start guides for different model types and quantization methods.

github

: 484

flute

FLUTE (Flexible Lookup Table Engine for LUT-quantized LLMs) is a tool designed for uniform quantization and lookup table quantization of weights in lower-precision intervals. It offers flexibility in mapping intervals to arbitrary values through a lookup table. FLUTE supports various quantization formats such as int4, int3, int2, fp4, fp3, fp2, nf4, nf3, nf2, and even custom tables. The tool also introduces new quantization algorithms like Learned Normal Float (NFL) for improved performance and calibration data learning. FLUTE provides benchmarks, model zoo, and integration with frameworks like vLLM and HuggingFace for easy deployment and usage.

github

: 229

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.

github

: 314

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.

github

: 6.5k

ruvector

github

: 442

kirara-ai

Kirara AI is a chatbot that supports mainstream large language models and chat platforms. It provides features such as image sending, keyword-triggered replies, multi-account support, personality settings, and support for various chat platforms like QQ, Telegram, Discord, and WeChat. The tool also supports HTTP server for Web API, popular large models like OpenAI and DeepSeek, plugin mechanism, conditional triggers, admin commands, drawing models, voice replies, multi-turn conversations, cross-platform message sending, custom workflows, web management interface, and built-in Frpc intranet penetration.

github

: 14.9k

ai-daily-digest

AI Daily Digest is a tool that fetches the latest articles from the top 90 Hacker News technology blogs recommended by Andrej Karpathy. It uses AI multi-dimensional scoring to curate a structured daily digest. The tool supports Gemini by default and can automatically degrade to OpenAI compatible API. It offers a five-step processing pipeline including RSS fetching, time filtering, AI scoring and classification, AI summarization and translation, and trend summarization. The generated daily digest includes sections like today's highlights, must-read articles, data overview, and categorized article lists. The tool is designed to be dependency-free, bilingual, with structured summaries, visual statistics, intelligent categorization, trend insights, and persistent configuration memory.

github

: 604

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.

github

: 71.1k

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.

github

: 342

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.

github

: 1.7k

tiny-llm-zh

github

: 147

examples

Cerebrium's official examples repository provides practical, ready-to-use examples for building Machine Learning / AI applications on the platform. The repository contains self-contained projects demonstrating specific use cases with detailed instructions on deployment. Examples cover a wide range of categories such as getting started, advanced concepts, endpoints, integrations, large language models, voice, image & video, migrations, application demos, batching, and Python apps.

github

: 454

HuaTuoAI

HuaTuoAI is an artificial intelligence image classification system specifically designed for traditional Chinese medicine. It utilizes deep learning techniques, such as Convolutional Neural Networks (CNN), to accurately classify Chinese herbs and ingredients based on input images. The project aims to unlock the secrets of plants, depict the unknown realm of Chinese medicine using technology and intelligence, and perpetuate ancient cultural heritage.

github

: 83

vector-inference

This repository provides an easy-to-use solution for running inference servers on Slurm-managed computing clusters using vLLM. All scripts in this repository run natively on the Vector Institute cluster environment. Users can deploy models as Slurm jobs, check server status and performance metrics, and shut down models. The repository also supports launching custom models with specific configurations. Additionally, users can send inference requests and set up an SSH tunnel to run inference from a local device.

github

: 77

mini-sglang

Mini-SGLang is a lightweight yet high-performance inference framework for Large Language Models. With a compact codebase of ~5,000 lines of Python, it serves as both a capable inference engine and a transparent reference for researchers and developers. It achieves state-of-the-art throughput and latency with advanced optimizations such as Radix Cache, Chunked Prefill, Overlap Scheduling, Tensor Parallelism, and Optimized Kernels integrating FlashAttention and FlashInfer for maximum efficiency. Mini-SGLang is designed to demystify the complexities of modern LLM serving systems, providing a clean, modular, and fully type-annotated codebase that is easy to understand and modify.

github

: 3.5k

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.

github

: 7.1k

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.

github

: 502

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.

github

: 159

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.

github

: 697

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.

github

: 27.7k

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

github

: 953

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.

github

: 1.3k

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.

github

: 2.2k