Video-LLaMA vs LLMs-from-scratch
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| Video-LLaMA | LLMs-from-scratch | |
|---|---|---|
| Tagline | Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding | Implement a ChatGPT-like LLM in PyTorch from scratch |
| Stars | 3.1k | 99k |
| Forks | 286 | 15k |
| Open issues | 69 | 4 |
| Language | Python | Jupyter Notebook |
| License | BSD-3-Clause | Other |
| Last pushed | Jun 4, 2024 | Jun 2, 2026 |
| Categories | AI Agents, Model Training, Inference & Serving | Model Training, LLM Frameworks |
Video-LLaMA
This repository hosts the Video-LLaMA project, focused on enhancing large language models with understanding of video and audio content. It provides functionalities for cross-modal pre-training and instruction tuning, aiming to improve multimodal understanding capabilities.
Python
LLMs-from-scratch
Repository containing code and instructions for developing, pretraining, and finetuning a GPT-like large language model (LLM) using PyTorch.
Jupyter Notebook