Stars
Robust recipes to align language models with human and AI preferences
Use PEFT or Full-parameter to finetune 400+ LLMs or 100+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-V…
🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型
Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
LLM based data scientist, AI native data application. AI-driven infinite thinking redefines BI.
ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型
Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
利用HuggingFace的官方下载工具从镜像网站进行高速下载。
小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.
🦜🔗 Build context-aware reasoning applications
Robust Speech Recognition via Large-Scale Weak Supervision
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
Common Voice is part of Mozilla's initiative to help teach machines how real people speak.