xverse-ai / XVERSE-V-13BLinks
☆79Updated last year
Alternatives and similar repositories for XVERSE-V-13B
Users that are interested in XVERSE-V-13B are comparing it to the libraries listed below
Sorting:
- Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data.☆234Updated 3 months ago
- 基于baichuan-7b的开源多模态大语言模型☆73Updated last year
- ☆173Updated 3 months ago
- Multimodal chatbot with computer vision capabilities integrated, our 1st-gen LMM☆101Updated last year
- ☆68Updated last year
- ☆28Updated last year
- SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama: https://arxiv.org/abs/2408.09333v2☆120Updated 6 months ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.☆37Updated 8 months ago
- ☆227Updated last year
- Chinese CLIP models with SOTA performance.☆55Updated last year
- 训练一个对中文支持更好的LLaVA模型,并开源训练代码和数据。☆59Updated 8 months ago
- ☆38Updated 7 months ago
- SUS-Chat: Instruction tuning done right☆48Updated last year
- The official code for NeurIPS 2024 paper: Harmonizing Visual Text Comprehension and Generation☆125Updated 6 months ago
- A light proxy solution for HuggingFace hub.☆46Updated last year
- Our 2nd-gen LMM☆33Updated last year
- MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval☆179Updated last week
- Its an open source LLM based on MOE Structure.☆58Updated 10 months ago
- Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models☆60Updated 7 months ago
- The official codes for "Aurora: Activating chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning"☆262Updated last year
- LongQLoRA: Extent Context Length of LLMs Efficiently☆165Updated last year
- GLM Series Edge Models☆139Updated 3 months ago
- 从零到一实现了一个多模态大模型,并命名为Reyes(睿视),R:睿,eyes:眼。Reyes的参数量为8B,视觉编码器使用的是InternViT-300M-448px-V2_5,语言模型侧使用的是Qwen2.5-7B-Instruct,Reyes也通过一个两层MLP投影层连…☆13Updated 3 months ago
- zero零训练llm调参☆31Updated last year
- 使用langchain进行任务规划,构建子任务的会话场景资源,通过MCTS任务执行器,来让每个子任务通过在上下文中资源,通过自身反思探索来获取自身对问题的最优答案;这种方式依赖模型的对齐偏好,我们在每种偏好上设计了一个工程框架,来完成自我对不同答案的奖励进行采样策略☆29Updated 3 weeks ago
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆138Updated last year
- Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines☆126Updated 6 months ago
- A Token-level Text Image Foundation Model for Document Understanding☆91Updated 3 weeks ago
- Offical Code for GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation☆138Updated 7 months ago
- MuLan: Adapting Multilingual Diffusion Models for 110+ Languages (无需额外训练为任意扩散模型支持多语言能力)☆135Updated 4 months ago