| ## 🎉 新闻 | |
| - [2024-10-11] [新文速递|PreparedLLM：高效训练领域大语言模型的“前预训练”框架](https://mp.weixin.qq.com/s/ugJQ9tbp6Y87xA3TOWteqw)。 | |
| - [2024-08-31] 文章[PreparedLLM: Effective Pre-pretraining Framework for Domain-specific Large Language Models](https://www.tandfonline.com/doi/full/10.1080/20964471.2024.2396159)已被*Big Earth Data*期刊接收。 | |
| - [2024-08-31] 发布[Chinese-Mistral-7B-Instruct-v0.2](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.2)对话模型。语言理解能力大幅提高，并且具备多轮对话能力。 | |
| - [2024-06-30] 发布[JiuZhou-Instruct-v0.2](https://huggingface.co/itpossible/JiuZhou-Instruct-v0.2)对话模型。语言理解能力大幅提高，并且具备多轮对话能力。 | |
| - [2024-04-04] 发布[Chinese-Mistral-7B-Instruct-v0.1](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.1)。 | |
| - [2024-03-31] 发布[JiuZhou-base](https://huggingface.co/itpossible/JiuZhou-base]和[Chinese-Mistral-7B-v0.1](https://huggingface.co/itpossible/Chinese-Mistral-7B)基座模型。 | |
| JiuZhou, a powerful bilingual LLM with 7 billion parameters developed by the Tsinghua research team.<br> | |
| Use case: We are using a widely circulated and interesting question.<br> | |
| Qestion: 9.11 and 9.9 - which is bigger?<br> | |
| · JiuZhou answer correctly. | |
|  | |
| · ChatGPT, Gemini, Moonshot Al, Qianwen, Mixtral 8x7B, Llama 3 all answer incorrectly. | |
|  | |