li563042811 Goto Github PK

grok-1

Grok open release

grpc-video-streaming

This code streams a video over the internet using Google remote procedural calls. The video is streamed from server to client, it is processed at the client and the results are sent back to the server.

hello-algo

《Hello 算法》：动画图解、一键运行的数据结构与算法教程，支持 Java, C++, Python, Go, JS, TS, C#, Swift, Rust, Dart, Zig 等语言。

how-to-ask-questions-the-smart-way

本文原文由知名 Hacker Eric S. Raymond 所撰寫，教你如何正確的提出技術問題並獲得你滿意的答案。

hugo

The world’s fastest framework for building websites.

icefall

job_test

研究生毕业秋招期间的笔试题目

k2

FSA/FST algorithms, intended to (eventually) be interoperable with PyTorch and similar

kaldi

This is the official location of the Kaldi project.

kaldi-avsr

Kaldi-based audio-visual speech recognition

kenlm

KenLM: Faster and Smaller Language Model Queries

languagebind

【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

lavit

LaVIT: Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization

leetcodetop

leveraging-self-supervised-learning-for-avsr

Official PyTorch implementation of paper Leveraging Unimodal Self Supervised Learning for Multimodal Audio-Visual Speech Recognition

lichao

lip-reading-deeplearning

:unlock: Lip Reading - Cross Audio-Visual Recognition using 3D Architectures

lip_reading_in_the_wild_avsr

Audio-Visual Speech Recognition using Deep Learning

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

llama

Inference code for LLaMA models

llama-adapter

Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

llama2-chinese

Llama中文社区，最好的中文Llama大模型，完全开源可商用

llasm

第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。

llava

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

llm-conversation-safety

[NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

lora

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

masr

中文语音识别; Mandarin Automatic Speech Recognition;

mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

metagpt

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

moe-llava

Mixture-of-Experts for Large Vision-Language Models