AlkeneSun's starred repositories
gpt4-captcha-bypass
Captcha Bypass using GPT4-o
Qwen2-Audio
The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.
Streamer-Sales
Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️
Index-1.9B
A SOTA lightweight multilingual LLM
GCMSFormer
A fully automatic method based on Transformer for resolution of overlapping peaks in gas chromatography-mass spectrometry
Self-Iterative-Agent-System-for-Complex-Problem-Solving
Multiple instructed-LLMs engage in multi-round "self-questioning" to seek the optimal solution, borrowing from the idea of debate, iteratively refining the current problem-solving process, and finally selecting the optimal solution to give a conclusion.
vision-agent
Vision agent
streaming-json-go
A simple, easy-to-use streaming json preprocessor.
FastGPT
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
llama3-from-scratch-zh
从零实现一个 llama3 中文版
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
llm-deploy
大模型/LLM推理和部署理论与实践
PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
ChatTTS-Forge
🍦 ChatTTS-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
voice_talk_chatgpt
基于Gradio开发的ChatGPT聊天应用，可以文字 或 语音对话，发送的音频通过OpenAI的STT转文本后，再通过ChatGPT生成回复，回复的内容通过OpenAI TTS合成后返回并自动播放，实现语音聊天功能。
opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.