Stars
MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition
A curated list of full-duplex spoken dialogue models
This is a repository for fine-tuning Qwen2-Audio, currently supporting Distributed Data Parallel (DDP) and DeepSpeed.
Official implementation of the paper titled "Age and Gender Recognition Using a Convolutional Neural Network with a Specially Designed Multi-Attention Module through Speech Spectrograms". This impl…
Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理
Fast and memory-efficient exact attention
本『ChatGPT资源库(原理/微调/代码/论文)』的初始版本来自July CSDN博客上阅读量高达50万的ChatGPT系列，联合发起人：七月ChatGPT原理课学员，6月初正式对外发布
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
Which Encoding is the Best for Text Classification in Chinese, English, Japanese and Korean?
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 Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
Simple XLNet implementation with Pytorch Wrapper