chat_glm6b0

此为chat_glm 预训练模型,ChatGLM-6B 是一个开源的、支持中英双语的对话语言模型，基于 General Language Model (GLM) 架构，具有 62 亿参数。结合模型量化技术，用户可以在消费级的显卡上进行本地部署（INT4 量化级别下最低只需 6GB 显存）。 ChatGLM-6B 使用了和 ChatGPT 相似的技术，针对中文问答和对话进行了优化。经过约 1T 标识符的中英双语训练，辅以监督微调、反馈自助、人类反馈强化学习等技术的加持，62 亿参数的 ChatGLM-6B 已经能生成相当符合人类偏好的回答，更多信息请参考我们的博客。 为了This is the pre-trained ChatGLM model. ChatGLM-6B is an open-source, Chinese-English bilingual conversational large language model based on the General Language Model (GLM) architecture, with 6.2 billion parameters. Leveraging model quantization technology, users can deploy it locally on consumer-grade graphics cards, with a minimum VRAM requirement of 6GB at the INT4 quantization level. ChatGLM-6B adopts technologies similar to those used in ChatGPT, and has been optimized for Chinese question answering and conversations. Trained on approximately 1 trillion tokens of Chinese-English bilingual corpora, and augmented with techniques such as supervised fine-tuning, feedback self-aided training, and reinforcement learning from human feedback, the 6.2-billion-parameter ChatGLM-6B is capable of generating responses that highly align with human preferences. For more information, please refer to our blog.

搜集汇总

背景与挑战

背景概述

该数据集为ChatGLM-6B预训练模型，是一个开源的、支持中英双语对话的语言模型，基于GLM架构并拥有62亿参数。它针对中文问答和对话进行了优化，结合模型量化技术，可在消费级显卡上部署，并经过大规模训练和多种技术加持以生成符合人类偏好的回答。