Trustfall is a query engine for querying any type of data source, from APIs and databases to any type of file on disk, even AI models. Trustfall Playground supports running queries against public data sources such as: For example, this linkShows the results of the HackerNews query: “Which GitHub or Twitter users are commenting on […]
ImageBind is an AI model that supports binding information from six different modalities (image, text, audio, depth, temperature, and IMU data), which unifies this information into a single embedded representation space, enabling machines to more comprehensively , learning directly from multiple information without explicit supervision (i.e., the process of organizing and labeling raw data). ImageBind
ImageBind Homepage, Documentation and Downloads- Multimodal AI Model- News Fast Delivery Read More »
Ink is a library that supports using React to build command-line applications—the same component-based UI building experience that React provides in the browser. It’s just that InK is geared towards command-line applications. So Ink is actually a React renderer, which converts the React component tree into a string, and then outputs it to the terminal.
SuperCLUE is an evaluation benchmark for general large models available in Chinese. The main question it answers is: the effect of the Chinese large-scale model under the current situation of vigorous development of the general-purpose large-scale model. including but not limited to: The effect of these models on different tasks To what extent
Chinese-LLaMA-Alpaca contains the Chinese LLaMA model and the Alpaca large model fine-tuned with instructions. Based on the original LLaMA, these models expand the Chinese vocabulary and use Chinese data for secondary pre-training, which further improves the ability to understand the basic semantics of Chinese. At the same time, the Chinese Alpaca model further uses Chinese
OpenLLaMA is an open source rendition of Meta AI’s LLaMA large language model under a permissive license. The repository contains a public preview of the trained 200 billion token 7B OpenLLaMA model, and provides PyTorch and Jax weights for the pretrained OpenLLaMA model, as well as evaluation results and comparisons to the original LLaMA model.
MLC LLM is a general solution that allows any language model to be deployed locally on various hardware backends and native applications. In addition, MLC LLM also provides an efficient framework for users to further optimize model performance according to their needs. MLC LLM is designed to enable everyone to develop, optimize and deploy AI
WizardLM is a fine-tuned 7B LLaMA model. It fine-tunes following the dialogue through a large number of commands of varying difficulty. The novelty of this model is the use of LLM to automatically generate training data. The WizardLM model uses a new method called Evol-Instruct (a new method to improve the ability of LLM by
SantaCoder is a language model with 1.1 billion parameters that can be used for code generation and completion suggestions in several programming languages such as Python, Java, and JavaScript. According to the official information, the basis for training SantaCoder is The Stack (v1.1) data set. Although SantaCoder is relatively small in size, with only 1.1
“Enlightenment” is a bilingual multimodal pre-training model with a scale of 1.75 trillion parameters.There are currently 7 open source model results in the project, and the model parameter files need to beEnlightenment platformMake a download request. Graphics CogView The CogView parameter is 4 billion. The model can generate images from text, and after fine-tuning, it
Baize is an open-source chat model trained with LoRA, which improves upon the open-source large-scale language model LLaMA by fine-tuning LLaMA with a newly generated chat corpus, which runs on a single GPU, making it available to a wider range of researchers . Bai Ze currently includes four models in English: Bai Ze-7B, 13B, and
Inlyne is a GPU powered but browserless A tool that helps you quickly view Markdown files in the blink of an eye. characteristic: browserless – One shouldn’t need electron or chrome to quickly view markdown files in a repository. GPU driver — thanks to WGPU project,Rendering can and will be done on the
This project provides the community withChinese dialogue model Linly-ChatFlow, Chinese basic model Linly-Chinese-LLaMA and their training data.model based on Tencent Pretrain The pre-training framework is realized, and the full-tuning on 32 * A100 GPU will gradually open up the Chinese model weights of 7B, 13B, 33B, and 65B scales. The Chinese basic model is based
AnyLabeling is an automatic labeling tool that can use YOLOv5, YOLOv8, Segment Anything, or a custom model for labeling. Image annotations for polygons, rectangles, circles, lines and points. Automatic labeling using YOLOv5 YOLOv8 and Segment Anything. Text detection, recognition and KIE (Key Information Extraction) tagging. Available in multiple languages: English, Vietnamese,
