🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

a state-of-the-art-level open visual language model | 多模态预训练模型

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

GPT4V-level open-source multi-modal model based on Llama3-8B

FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

Official repository for LongChat and LongEval

星辰语义大模型TeleChat2是由中国电信人工智能研究院研发训练的大语言模型，是首个完全国产算力训练并开源的千亿参数模型

（1）弹性区间标准化的旋转位置词嵌入编码器+peft LORA量化训练，提高万级tokens性能支持。（2）证据理论解释学习，提升模型的复杂逻辑推理能力（3）兼容alpaca数据格式。

OpenAI style standard streaming multi-turn dialogue interface WEB API.