yangbang18
Follow
Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"
[NeurIPS 2024] Mitigating Object Hallucination via Concentric Causal Attention
[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
[CVPRW 2024] TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning. Official code for the 3rd place solution of the AI City Challenge 2024 Track 2.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.
ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.
A Flexible and Powerful Parameter Server for large-scale machine learning
MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video”
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch
Making large AI models cheaper, faster and more accessible
PyTorch code and models for the DINOv2 self-supervised learning method.
[CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models
The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models
Radiology Report Generation with Frozen LLMs
A method to increase the speed and lower the memory footprint of existing vision transformers.