Python tool for converting files and office documents to Markdown.

Understand Human Behavior to Align True Needs

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

灵积 / 通义千问 Java SDK

Qwen2 inference in Java

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Data processing with ML, LLM and Vision LLM

GLM-4-Voice | 端到端中英语音对话模型

Performant financial charts built with HTML5 canvas

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

Accessible large language models via k-bit quantization for PyTorch.

🔊 Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. 🎧👥📊 Advanced audio processing.

COYO-700M: Large-scale Image-Text Pair Dataset

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

Pure Java Llama2 inference with optional multi-GPU CUDA implementation

https://openjdk.org/projects/babylon

An extension to Llama2.java implementation accelerated with GPUs, using TornadoVM

Practical Llama 3 inference in Java

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Java client library for OpenAI API.Full support for all OpenAI API models including Completions, Chat, Edits, Embeddings, Audio, Files, Assistants-v2, Images, Moderations, Batch, and Fine-tuning.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

A package for ontology engineering with deep learning and language models.

Low-Rank adapter extraction for fine-tuned transformers models

Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

More relighting!

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

[ACL 2022] A hierarchical table dataset for question answering and data-to-text generation.