Use PEFT or Full-parameter to finetune 300+ LLMs or 60+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V-2.6, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

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, le…

🦜🔗 Build context-aware reasoning applications

Streamlit — A faster way to build and share data apps.

An MBTI Exploration of Large Language Models

Training Microsoft Phi 2 LLM for sequence classification with LoRA and QLoRA

Classy-fire is multiclass text classification approach leveraging OpenAI LLM model APIs optimally using clever parameter tuning and prompting.

Gemma-SFT, gemma-2b/gemma-7b微调(finetune,transformers)/LORA(peft)/推理(inference)

A Native-PyTorch Library for LLM Fine-tuning

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Transformer: PyTorch Implementation of "Attention Is All You Need"

The official PyTorch implementation of Google's Gemma models

Official PyTorch implementation of Enhancing Multi-Label Classifcation via Dynamic Label-Order Learning (AAAI 2024)

An awesome paper list of fake news detection (FND) and rumor detection.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

[ACL2023] Code and dataset for paper "MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System"

[ICLR 2024 (Spotlight)] "Frozen Transformers in Language Models are Effective Visual Encoder Layers"

Official Code for the WWW'24 Paper: "Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models"

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

该仓库主要记录 NLP 算法工程师相关的面试题

Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用

新浪微博爬虫，用python爬取新浪微博数据

新浪微博爬虫，用python爬取新浪微博数据，并下载微博图片和微博视频

中文谣言和虚假新闻数据集

快应用的示例项目，方便开发者了解各方面的快应用能力，如：框架，组件，接口等

An SE(3)-invariant autoencoder for generating the periodic structure of materials [ICLR 2022]

kaldi-asr/kaldi is the official location of the Kaldi project.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.