#jupyter_notebook #computer_vision #course #deep_learning #machine_learning #materials #natural_language_processing #python #pytorch #reinforcement_learning #seminars

https://github.com/girafe-ai/ml-course

#python #computer_vision #machine_learning #multimodal #natural_language_processing #pretrained_language_model #speech_processing #transformer #translation

https://github.com/microsoft/torchscale

#python #bert #deep_learning #language_model #language_models #machine_learning #natural_language_processing #nlp #pytorch #transformer

https://github.com/extreme-bert/extreme-bert

#jupyter_notebook #articles #artificial_intelligence #data_analysis #data_science #data_visualization #machine_learning #natural_language_processing #python #scraping #time_series

https://github.com/khuyentran1401/Data-science

#html #data_pipelines #deep_learning #document_ai #document_image_analysis #document_image_processing #document_parser #document_parsing #docx #donut #information_retrieval #langchain #machine_learning #ml #natural_language_processing #nlp #ocr #pdf #pdf_to_json #pdf_to_text #preprocessing

https://github.com/Unstructured-IO/unstructured

#python #deep_learning #flax #jax #language_model #large_language_models #natural_language_processing #transformer

https://github.com/young-geng/EasyLM

#python #chatgpt #clip #deep_learning #gpt #hacktoberfest #hnsw #information_retrieval #knn #large_language_models #machine_learning #machinelearning #multi_modal #natural_language_processing #search_engine #semantic_search #tensor_search #transformers #vector_search #vision_language #visual_search

https://github.com/marqo-ai/marqo

#python #active_learning #ai #annotation_tool #developer_tools #gpt_4 #human_in_the_loop #langchain #llm #machine_learning #mlops #natural_language_processing #nlp #rlhf #text_annotation #text_labeling #weak_supervision #weakly_supervised_learning

https://github.com/argilla-io/argilla

#jupyter_notebook #automated_machine_learning #automl #classification #data_science #deep_learning #finetuning #hyperparam #hyperparameter_optimization #jupyter_notebook #machine_learning #natural_language_generation #natural_language_processing #python #random_forest #regression #scikit_learn #tabular_data #timeseries_forecasting #tuning

https://github.com/microsoft/FLAML

#python #book #chinese #computer_vision #deep_learning #machine_learning #natural_language_processing #notebook #python

This resource, "Dive into Deep Learning," is a free online book that helps you learn deep learning by doing. It provides detailed concepts, background knowledge, and executable code to help you understand the mathematical principles and implement them in practice. The book includes runnable code examples so you can see how to solve problems step-by-step and experiment with different approaches. It also allows for community feedback and continuous updates to keep up with the rapidly evolving field of deep learning. This makes it an excellent resource for anyone looking to become a deep learning practitioner, whether you're a student or an industry professional.

https://github.com/d2l-ai/d2l-zh

#python #bert #deep_learning #flax #hacktoberfest #jax #language_model #language_models #machine_learning #model_hub #natural_language_processing #nlp #nlp_library #pretrained_models #python #pytorch #pytorch_transformers #seq2seq #speech_recognition #tensorflow #transformer

The Hugging Face Transformers library provides thousands of pretrained models for various tasks like text, image, and audio processing. These models can be used for tasks such as text classification, image detection, speech recognition, and more. The library supports popular deep learning frameworks like JAX, PyTorch, and TensorFlow, making it easy to switch between them.

The benefit to the user is that you can quickly download and use these pretrained models with just a few lines of code, saving time and computational resources. You can also fine-tune these models on your own datasets and share them with the community. Additionally, the library offers a simple `pipeline` API for immediate use on different inputs, making it user-friendly for both researchers and practitioners. This helps in reducing compute costs and carbon footprint while enabling high-performance results across various machine learning tasks.

https://github.com/huggingface/transformers

#python #autogluon #automated_machine_learning #automl #computer_vision #data_science #deep_learning #ensemble_learning #forecasting #gluon #hyperparameter_optimization #machine_learning #natural_language_processing #object_detection #python #pytorch #scikit_learn #structured_data #tabular_data #time_series #transfer_learning

AutoGluon makes machine learning easy and fast. With just a few lines of code, you can train and use high-accuracy models for images, text, time series, and tabular data. This means you can quickly build and deploy powerful machine learning models without needing to write a lot of code. It supports Python 3.8 to 3.11 and works on Linux, MacOS, and Windows, making it convenient for various users. This saves time and effort, allowing you to focus on other parts of your project.

https://github.com/autogluon/autogluon

#python #chinese #flash_attention #large_language_models #llm #natural_language_processing #pretrained_models

The Qwen series includes powerful language models and chat models that can be used for various tasks such as chatting, content creation, information extraction, summarization, translation, coding, and more. Here are the key benefits and features Qwen offers base language models (Qwen-1.8B, Qwen-7B, Qwen-14B, Qwen-72B) and chat models (Qwen-1.8B-Chat, Qwen-7B-Chat, Qwen-14B-Chat, Qwen-72B-Chat) with different sizes and capabilities.
- **Performance** The models are available in quantized forms (Int4 and Int8) which reduce memory usage and improve inference speed without significant performance degradation.
- **System Prompt** The models can use tools, act as agents, or even interpret code, with good performance on code execution and tool-use benchmarks.
- **Long-Context Understanding** Easy deployment options include using vLLM, FastChat, Web UI demos, CLI demos, and OpenAI-style APIs.
- **Finetuning**: Scripts are provided for finetuning the models using full-parameter, LoRA, and Q-LoRA methods.

Overall, Qwen models offer robust performance, flexibility, and ease of use, making them suitable for a wide range of applications.

https://github.com/QwenLM/Qwen

#jupyter_notebook #computer_vision #ethical_hacking #face_detection #machine_learning #natural_language_processing #network_analysis #network_programming #network_security #programming_tutorial #python #python_tutorials #python3 #scapy #scapy_tutorials #socket_programming #text_classification #tutorials #web_scraping

This repository offers a wide range of Python tutorials and projects, covering various topics such as ethical hacking, machine learning, web scraping, GUI programming, game development, and more. You can learn how to perform network manipulation, build machine learning models, scrape websites, create GUI applications, develop games, and much more. The tutorials are well-structured and include code examples, making it easy to follow along and implement the projects yourself. This resource is beneficial for both beginners and advanced users looking to expand their Python skills in different areas.

https://github.com/x4nth055/pythoncode-tutorials

#python #applicant_tracking_system #ats #hacktoberfest #machine_learning #natural_language_processing #nextjs #python #resume #resume_builder #resume_parser #text_similarity #typescript #vector_search #word_embeddings

Resume Matcher is a free and open-source tool that helps you tailor your resume to a job description. It uses AI to extract important keywords from the job description and matches them with your resume, improving its readability and making it more likely to pass through applicant tracking systems (ATS). Here’s how it benefits you: it analyzes your resume and job descriptions, identifies key terms, and suggests improvements to increase your chances of getting noticed by employers. This tool is easy to install and use, and it's available for free, making it a valuable resource for anyone looking to enhance their job application process.

https://github.com/srbhr/Resume-Matcher

#python #ai #artificial_intelligence #cython #data_science #deep_learning #entity_linking #machine_learning #named_entity_recognition #natural_language_processing #neural_network #neural_networks #nlp #nlp_library #python #spacy #text_classification #tokenization

spaCy is a powerful tool for understanding and processing human language. It helps computers analyze text by breaking it into parts like words, sentences, and entities (like names or places). This makes it useful for tasks such as identifying who is doing what in a sentence or finding specific information from large texts. Using spaCy can save time and improve accuracy compared to manual analysis. It supports many languages and integrates well with advanced models like BERT, making it ideal for real-world applications.

https://github.com/explosion/spaCy

#python #agent #ai_societies #artificial_intelligence #communicative_ai #cooperative_ai #deep_learning #large_language_models #multi_agent_systems #natural_language_processing

CAMEL-AI is a community-driven project focused on multi-agent systems. It helps researchers study how AI agents interact and behave in large-scale environments. This platform supports tasks like data generation, task automation, and world simulation. By using CAMEL-AI, users can create complex scenarios where multiple agents collaborate to solve problems or generate synthetic data. The benefits include gaining insights into agent behaviors, improving decision-making processes, and enhancing collaboration among AI entities. It's open-source and easy to install via PyPI.

https://github.com/camel-ai/camel

#python #bot #bot_framework #botkit #bots #chatbot #chatbots #chatbots_framework #conversation_driven_development #conversational_agents #conversational_ai #conversational_bots #machine_learning #machine_learning_library #mitie #natural_language_processing #nlp #nlu #rasa #spacy #wit

Rasa is an open-source framework that helps build advanced chatbots. It allows developers to create contextual assistants that can have layered conversations, making interactions more natural. Rasa supports integration with various platforms like Facebook Messenger, Slack, and Google Home Actions. This flexibility and customization capability make it a popular choice for businesses to automate customer support and enhance user experience. By using Rasa, users can create intelligent chatbots that understand and respond to user inputs effectively, improving communication and engagement.

https://github.com/RasaHQ/rasa

#typescript #ai #chatgpt #docsgpt #hacktoberfest #information_retrieval #language_model #llm #machine_learning #natural_language_processing #python #pytorch #rag #react #semantic_search #transformers #web_app

DocsGPT is an open-source AI tool that helps you quickly find accurate answers from many types of documents and web sources without errors. It supports formats like PDF, DOCX, images, and integrates with websites, APIs, and chat platforms like Discord and Telegram. You can deploy it privately for security, customize it to fit your brand, and connect it to tools for advanced actions. This means you save time searching for information, get reliable answers with sources, and improve productivity whether you’re a developer, support team, or business user. It’s easy to set up and scales well for many users[2][3][4].

https://github.com/arc53/DocsGPT

#python #large_language_models #machine_learning_systems #natural_language_processing

Flash Linear Attention (FLA) is a fast, memory-efficient library for advanced linear attention models used in transformers, written in PyTorch and Triton, and compatible with NVIDIA, AMD, and Intel GPUs. It offers many state-of-the-art linear attention models and fused modules that speed up training and reduce memory use. You can easily replace standard attention layers in your models with FLA’s efficient versions, improving training and inference speed, especially for long sequences. FLA supports hybrid models mixing linear and standard attention, and integrates with Hugging Face Transformers for easy use and evaluation. This helps you train and run large language models faster and with less memory, making your AI projects more efficient and scalable.

https://github.com/fla-org/flash-linear-attention