--- license: apache-2.0 language: - zh - en --- # BlueLM

🖥 github • 📜 LICENSE • 🎯 vivo Developers • 🗨 WeChat

## 模型介绍/Introduction BlueLM 是由 vivo AI 全球研究院自主研发的大规模预训练语言模型，本次发布包含 7B 基础模型和 7B 对话模型，同时我们开源了支持 **32K** 的长文本基础模型和对话模型。 - **更大量的优质数据**：高质量语料库进行训练，规模达到了 **2.6 万亿** 的 token 数，该语料库包含中文、英文以及少量日韩数据。 - **更优的效果**：其中 BlueLM-7B-Chat 在 **C-Eval** 和 **CMMLU** 上均取得领先结果，对比同尺寸开源模型中具有较强的竞争力。 - **长文本支持**：BlueLM-7B-Base-32K 和 BlueLM-7B-Chat-32K 均支持 **32K** 长文本，在保持基础能力相当情况下，能够支持更长上下文理解。 - **协议说明**：BlueLM 系列欢迎开发者进行学术研究和商业应用。 BlueLM is a large-scale open-source language model independently developed by the vivo AI Lab. This release includes 2K and 32K context length versions for both Base and Chat models. - **High-quality Data**: BlueLM is trained on a high-quality data with 2.6 trillion tokens. Our train corpus mainly consists of Chinese and English data, with a small amount of Japanese and Korean data. - **Stronger Performance**: BlueLM-7B-Chat achieves a strong competitive performance in C-Eval and CMMLU benchmarks of the same size. - **Longer Context**: We have extended the context length of both BlueLM-7B-Base-32K and BlueLM-7B-Chat-32K models from 2K to 32K. The models can support longer context understanding while maintaining the same basic capabilities. - **Model License**: BlueLM weights are open for academic research and commercial use. 本次发布基座模型下载链接见： The release versions and hugging face download links are listed in the table below: | | Base Model | Chat Model | 4bits Quantized Chat Model | |:---:|:--------------------:|:--------------------:|:--------------------------:| | 7B-2k | [BlueLM-7B-Base](https://huggingface.co/vivo-ai/BlueLM-7B-Base) | [BlueLM-7B-Chat](https://huggingface.co/vivo-ai/BlueLM-7B-Chat) | [BlueLM-7B-Chat-4bits](https://huggingface.co/vivo-ai/BlueLM-7B-Chat-4bits) | | 7B-32K | [BlueLM-7B-Base-32K](https://huggingface.co/vivo-ai/BlueLM-7B-Base-32K) | [BlueLM-7B-Chat-32K](https://huggingface.co/vivo-ai/BlueLM-7B-Chat-32K) | [BlueLM-7B-Chat-32K-AWQ](https://huggingface.co/vivo-ai/BlueLM-7B-Chat-32K-AWQ) / [BlueLM-7B-Chat-32K-GPTQ](https://huggingface.co/vivo-ai/BlueLM-7B-Chat-32K-GPTQ) | ## 评测结果/Benchmark Results 我们在 LongBench 评测集上对我们的 BlueLM-7B-Chat-32K 模型进行了测试，具体结果如下表所示： We tested our BlueLM-7B-Chat-32K on the LongBench dataset and the results are shown in the table below: | Model | Average | Summary | Single-Doc QA | Multi-Doc QA | Code | Few-shot | Synthetic | |:----------------------|:-----|:---------|:--------------|:--------------|:------|:---------|:----------| | BlueLM-7B-Chat-32K | 41.2 | 18.8 | 35.6 | 36.2 | 54.2 | 56.9 | 45.5 | ## 推理部署/Inference and Deployment ```python >>> import torch >>> from transformers import AutoModelForCausalLM, AutoTokenizer >>> tokenizer = AutoTokenizer.from_pretrained("vivo-ai/BlueLM-7B-Chat-32K-AWQ", trust_remote_code=True, use_fast=False) >>> model = AutoModelForCausalLM.from_pretrained("vivo-ai/BlueLM-7B-Chat-32K-AWQ", device_map="cuda:0", torch_dtype=torch.float16, trust_remote_code=True, low_cpu_mem_usage=True, use_cache=False) >>> model = model.eval() >>> inputs = tokenizer("[|Human|]:写一篇关于刘慈欣《三体》小说的读后感，1000字左右[|AI|]:", return_tensors="pt") >>> inputs = inputs.to("cuda:0") >>> pred = model.generate(**inputs, max_new_tokens=2048, repetition_penalty=1.1) >>> print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True)) ``` 更多使用说明，请参考我们的 [Github 仓库](https://github.com/vivo-ai-lab/BlueLM)。 For more instructions, please refer to our [Github Repo](https://github.com/vivo-ai-lab/BlueLM). ## 协议/License 社区使用代码依照 [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) 协议开源，且使用 BlueLM 模型权重需要遵循 [vivo_BlueLM模型许可协议](https://huggingface.co/vivo-ai/BlueLM-7B-Chat-32K-AWQ/blob/main/MODEL_LICENSE)。 Our code is licensed under the [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) and [Community License for BlueLM Model](https://huggingface.co/vivo-ai/BlueLM-7B-Chat-32K-AWQ/blob/main/MODEL_LICENSE).