TalkUHulk
Follow
LLM
[CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
A lightweight flexible Video-MLLM developed by TencentQQ Multimedia Research Team.
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理
llama3 implementation one matrix multiplication at a time
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
[NeurIPS 2024] Efficient Multi-modal Models via Stage-wise Visual Context Compression
AgentTuning: Enabling Generalized Agent Abilities for LLMs
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
《大模型白盒子构建指南》：一个全手搓的Tiny-Universe
[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
Phi-3.5 for Mac: Locally-run Vision and Language Models for Apple Silicon
Run PyTorch LLMs locally on servers, desktop and mobile
MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.
the resources about the application based on LLM with RAG pattern
MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
A quick guide (especially) for trending instruction finetuning datasets
A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。
GAOKAO-Bench is an evaluation framework that utilizes GAOKAO questions as a dataset to evaluate large language models.
[COLING 2022] CSL: A Large-scale Chinese Scientific Literature Dataset 中文科学文献数据集
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.