LLaMA-Omni vs LLMs-from-scratch
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| LLaMA-Omni | LLMs-from-scratch | |
|---|---|---|
| Tagline | LLaMA-Omni is a speech interaction model built upon Llama-3.1-8B-Instruct, allowing for seamless low-latency speech-to-speech and speech-to-text interactions. | Implement a ChatGPT-like LLM in PyTorch from scratch |
| Stars | 3.1k | 99k |
| Forks | 223 | 15k |
| Open issues | 52 | 4 |
| Language | Python | Jupyter Notebook |
| License | Apache-2.0 | Other |
| Last pushed | May 19, 2025 | Jun 2, 2026 |
| Categories | Speech & Audio | Model Training, LLM Frameworks |
LLaMA-Omni
This repository contains the source code for LLaMA-Omni, an innovative end-to-end speech interaction system that generates both text and speech responses based on speech inputs, with a latency as low as 226ms. It features advanced training techniques and is available in varying parameter sizes.
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