Stars
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。
基于pytorch的中文意图识别和槽位填充
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4…
AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目
基于pytorch_bert的中文多标签分类
an implementation of Self-Extend, to expand the context window via grouped attention
一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。
⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
booydar / LM-RMT
Forked from kimiyoung/transformer-xlRecurrent Memory Transformer
[NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…
Comparison of RoPE and xPos positional embeddings used in LLMs
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Aligning pretrained language models with instruction data generated by themselves.
新闻联播文字稿及其基于 nodejs 的爬虫源码 (利用 Github Actions 实现自动更新)
轻松玩转LLM兼容openai&langchain，支持文心一言、讯飞星火、腾讯混元、智谱ChatGLM等
crawl the public files of different governments through python 3.
利用Python爬取网站近年的政府工作报告，并进行简单的词频分析+词云