feat(model): Support llama3.1 models (#1744)

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)

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)

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)

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}"

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"),

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)

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!

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

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

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: {