diff --git a/README.ja.md b/README.ja.md index c0d2423ff..e8b794db7 100644 --- a/README.ja.md +++ b/README.ja.md @@ -154,6 +154,9 @@ DB-GPTのアーキテクチャは以下の図に示されています： 私たちは、LLaMA/LLaMA2、Baichuan、ChatGLM、Wenxin、Tongyi、Zhipuなど、オープンソースおよびAPIエージェントからの数十の大規模言語モデル（LLM）を含む幅広いモデルをサポートしています。 - ニュース + - 🔥🔥🔥 [Meta-Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct) + - 🔥🔥🔥 [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct) + - 🔥🔥🔥 [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) - 🔥🔥🔥 [gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it) - 🔥🔥🔥 [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) - 🔥🔥🔥 [DeepSeek-Coder-V2-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct) diff --git a/README.md b/README.md index f558aa413..edb05a8a8 100644 --- a/README.md +++ b/README.md @@ -158,6 +158,9 @@ At present, we have introduced several key features to showcase our current capa We offer extensive model support, including dozens of large language models (LLMs) from both open-source and API agents, such as LLaMA/LLaMA2, Baichuan, ChatGLM, Wenxin, Tongyi, Zhipu, and many more. - News + - 🔥🔥🔥 [Meta-Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct) + - 🔥🔥🔥 [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct) + - 🔥🔥🔥 [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) - 🔥🔥🔥 [gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it) - 🔥🔥🔥 [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) - 🔥🔥🔥 [DeepSeek-Coder-V2-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct) diff --git a/README.zh.md b/README.zh.md index 9d7b7b03d..636e4d0b1 100644 --- a/README.zh.md +++ b/README.zh.md @@ -152,6 +152,9 @@ 海量模型支持，包括开源、API代理等几十种大语言模型。如LLaMA/LLaMA2、Baichuan、ChatGLM、文心、通义、智谱等。当前已支持如下模型: - 新增支持模型 + - 🔥🔥🔥 [Meta-Llama-3.1-405B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-405B-Instruct) + - 🔥🔥🔥 [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct) + - 🔥🔥🔥 [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) - 🔥🔥🔥 [gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it) - 🔥🔥🔥 [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) - 🔥🔥🔥 [DeepSeek-Coder-V2-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct) diff --git a/dbgpt/agent/expand/resources/search_tool.py b/dbgpt/agent/expand/resources/search_tool.py index ff5b48be8..db7cf9917 100644 --- a/dbgpt/agent/expand/resources/search_tool.py +++ b/dbgpt/agent/expand/resources/search_tool.py @@ -38,6 +38,7 @@ def baidu_search( "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:112.0) " "Gecko/20100101 Firefox/112.0" } + num_results = int(num_results) if num_results < 8: num_results = 8 url = f"https://www.baidu.com/s?wd={query}&rn={num_results}" diff --git a/dbgpt/configs/model_config.py b/dbgpt/configs/model_config.py index 191c1a789..bd28072fc 100644 --- a/dbgpt/configs/model_config.py +++ b/dbgpt/configs/model_config.py @@ -85,6 +85,15 @@ def get_device() -> str: "meta-llama-3-8b-instruct": os.path.join(MODEL_PATH, "Meta-Llama-3-8B-Instruct"), # https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct "meta-llama-3-70b-instruct": os.path.join(MODEL_PATH, "Meta-Llama-3-70B-Instruct"), + "meta-llama-3.1-8b-instruct": os.path.join( + MODEL_PATH, "Meta-Llama-3.1-8B-Instruct" + ), + "meta-llama-3.1-70b-instruct": os.path.join( + MODEL_PATH, "Meta-Llama-3.1-70B-Instruct" + ), + "meta-llama-3.1-405b-instruct": os.path.join( + MODEL_PATH, "Meta-Llama-3.1-405B-Instruct" + ), "baichuan-13b": os.path.join(MODEL_PATH, "Baichuan-13B-Chat"), # please rename "fireballoon/baichuan-vicuna-chinese-7b" to "baichuan-7b" "baichuan-7b": os.path.join(MODEL_PATH, "baichuan-7b"), diff --git a/dbgpt/model/adapter/hf_adapter.py b/dbgpt/model/adapter/hf_adapter.py index 9e4180ba9..415a16a58 100644 --- a/dbgpt/model/adapter/hf_adapter.py +++ b/dbgpt/model/adapter/hf_adapter.py @@ -403,7 +403,12 @@ class Llama3Adapter(NewHFChatModelAdapter): support_8bit: bool = True def do_match(self, lower_model_name_or_path: Optional[str] = None): - return lower_model_name_or_path and "llama-3" in lower_model_name_or_path + return ( + lower_model_name_or_path + and "llama-3" in lower_model_name_or_path + and "instruct" in lower_model_name_or_path + and "3.1" not in lower_model_name_or_path + ) def get_str_prompt( self, @@ -431,6 +436,22 @@ def get_str_prompt( return str_prompt +class Llama31Adapter(Llama3Adapter): + def check_transformer_version(self, current_version: str) -> None: + logger.info(f"Checking transformers version: Current version {current_version}") + if not current_version >= "4.43.0": + raise ValueError( + "Llama-3.1 require transformers.__version__>=4.43.0, please upgrade your transformers package." + ) + + def do_match(self, lower_model_name_or_path: Optional[str] = None): + return ( + lower_model_name_or_path + and "llama-3.1" in lower_model_name_or_path + and "instruct" in lower_model_name_or_path + ) + + class DeepseekV2Adapter(NewHFChatModelAdapter): support_4bit: bool = False support_8bit: bool = False @@ -613,6 +634,7 @@ def load(self, model_path: str, from_pretrained_kwargs: dict): register_model_adapter(QwenAdapter) register_model_adapter(QwenMoeAdapter) register_model_adapter(Llama3Adapter) +register_model_adapter(Llama31Adapter) register_model_adapter(DeepseekV2Adapter) register_model_adapter(DeepseekCoderV2Adapter) register_model_adapter(SailorAdapter) diff --git a/docs/blog/2024-07-24-db-gpt-llama-3.1-support.md b/docs/blog/2024-07-24-db-gpt-llama-3.1-support.md new file mode 100644 index 000000000..740c2a932 --- /dev/null +++ b/docs/blog/2024-07-24-db-gpt-llama-3.1-support.md @@ -0,0 +1,66 @@ +--- +slug: db-gpt-llama-3.1-support +title: DB-GPT Now Supports Meta Llama 3.1 Series Models +authors: fangyinc +tags: [llama, LLM] +--- + +We are thrilled to announce that DB-GPT now supports inference with the Meta Llama 3.1 series models! + +## Introducing Meta Llama 3.1 + +Meta Llama 3.1 is a state-of-the-art series of language models developed by Meta AI. Designed with cutting-edge techniques, the Llama 3.1 models offer unparalleled performance and versatility. Here are some of the key highlights: + +- **Variety of Models**: Meta Llama 3.1 is available in 8B, 70B, and 405B versions, each with both instruction-tuned and base models, supporting contexts up to 128k tokens. +- **Multilingual Support**: Supports 8 languages, including English, German, and French. +- **Extensive Training**: Trained on over 1.5 trillion tokens, utilizing 250 million human and synthetic samples for fine-tuning. +- **Flexible Licensing**: Permissive model output usage allows for adaptation into other large language models (LLMs). +- **Quantization Support**: Available in FP8, AWQ, and GPTQ quantized versions for efficient inference. +- **Performance**: The Llama 3 405B version has outperformed GPT-4 in several benchmarks. +- **Enhanced Efficiency**: The 8B and 70B models have seen a 12% improvement in coding and instruction-following capabilities. +- **Tool and Function Call Support**: Supports tool usage and function calling. + +## How to Access Meta Llama 3.1 + +Your can access the Meta Llama 3.1 models according to [Access to Hugging Face](https://github.com/meta-llama/llama-models?tab=readme-ov-file#access-to-hugging-face). + +For comprehensive documentation and additional details, please refer to the [model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md). + +## Using Meta Llama 3.1 in DB-GPT + +Please read the [Source Code Deployment](../docs/installation/sourcecode) to learn how to install DB-GPT from source code. + +Llama 3.1 needs upgrade your transformers >= 4.43.0, please upgrade your transformers: +```bash +pip install --upgrade "transformers>=4.43.0" +``` + +Please cd to the DB-GPT root directory: +```bash +cd DB-GPT +``` + +We assume that your models are stored in the `models` directory, e.g., `models/Meta-Llama-3.1-8B-Instruct`. + +Then modify your `.env` file: +```env +LLM_MODEL=meta-llama-3.1-8b-instruct +# LLM_MODEL=meta-llama-3.1-70b-instruct +# LLM_MODEL=meta-llama-3.1-405b-instruct +## you can also specify the model path +# LLM_MODEL_PATH=models/Meta-Llama-3.1-8B-Instruct +## Quantization settings +# QUANTIZE_8bit=False +# QUANTIZE_4bit=True +## You can configure the maximum memory used by each GPU. +# MAX_GPU_MEMORY=16Gib +``` + +Then you can run the following command to start the server: +```bash +dbgpt start webserver +``` + +Open your browser and visit `http://localhost:5670` to use the Meta Llama 3.1 models in DB-GPT. + +Enjoy the power of Meta Llama 3.1 in DB-GPT! diff --git a/docs/blog/authors.yml b/docs/blog/authors.yml new file mode 100644 index 000000000..0613184fc --- /dev/null +++ b/docs/blog/authors.yml @@ -0,0 +1,5 @@ +fangyinc: + name: Fangyin Cheng + title: DB-GPT Core Team + url: https://github.com/fangyinc + image_url: https://avatars.githubusercontent.com/u/22972572?v=4 \ No newline at end of file diff --git a/docs/blog/tags.yml b/docs/blog/tags.yml new file mode 100644 index 000000000..1b600ac39 --- /dev/null +++ b/docs/blog/tags.yml @@ -0,0 +1,8 @@ +llama: + label: LLama + permalink: /llama + description: A series of language models developed by Meta AI +LLM: + label: LLM + permalink: /llm + description: Large Language Models diff --git a/docs/docusaurus.config.js b/docs/docusaurus.config.js index cb57427ee..ab8585bca 100755 --- a/docs/docusaurus.config.js +++ b/docs/docusaurus.config.js @@ -175,7 +175,9 @@ const config = { pages: { remarkPlugins: [require("@docusaurus/remark-plugin-npm2yarn")], }, - + blog: { + showReadingTime: true, + }, theme: { customCss: require.resolve('./src/css/custom.css'), }, @@ -248,6 +250,7 @@ const config = { position: 'left', label: "中文文档", }, + {to: '/blog', label: 'Blog', position: 'left'}, ], }, footer: {