From d309e60c5ebf613994ed26a9873cd1511762e9a3 Mon Sep 17 00:00:00 2001 From: huangyuyang <410644548@qq.com> Date: Tue, 9 Jul 2024 08:30:15 +0000 Subject: [PATCH] update readme --- README.md | 8 ++++---- README_EN.md | 8 ++++---- 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 4c5f3e92..9f094313 100644 --- a/README.md +++ b/README.md @@ -41,7 +41,7 @@ bash install.sh -DUSE_CUDA=ON # 编译GPU版本 ### 运行demo程序 (python) -假设我们的模型位于"/mnt/hfmodels/Qwen/Qwen2-7B-Instruct/"目录 +假设我们的模型位于"~/Qwen2-7B-Instruct/"目录 编译完成后可以使用下列demo: @@ -70,10 +70,10 @@ python3 -m ftllm.server -t 16 -p ~/Qwen2-7B-Instruct/ --port 8080 --model_name q # 进入fastllm/build-fastllm目录 # 命令行聊天程序, 支持打字机效果 (只支持Linux) -./main -p model.flm +./main -p ~/Qwen2-7B-Instruct/ # 简易webui, 使用流式输出 + 动态batch,可多路并发访问 -./webui -p model.flm --port 1234 +./webui -p ~/Qwen2-7B-Instruct/ --port 1234 ``` Windows下的编译推荐使用Cmake GUI + Visual Studio,在图形化界面中完成。 @@ -85,7 +85,7 @@ Windows下的编译推荐使用Cmake GUI + Visual Studio,在图形化界面中 ``` python # 模型创建 from ftllm import llm -model = llm.model("model.flm") +model = llm.model("~/Qwen2-7B-Instruct/") # 生成回复 print(model.response("你好")) diff --git a/README_EN.md b/README_EN.md index e13202c2..e89a7fb0 100644 --- a/README_EN.md +++ b/README_EN.md @@ -39,7 +39,7 @@ For compilation on other platforms, refer to the documentation: ### Running the demo program (python) -Assuming our model is located in the "/mnt/hfmodels/Qwen/Qwen2-7B-Instruct/" directory: +Assuming our model is located in the "~/Qwen2-7B-Instruct/" directory: After compilation, you can use the following demos: @@ -68,10 +68,10 @@ For architectures that cannot directly read Hugging Face models, refer to [Model # Enter the fastllm/build-fastllm directory # Command line chat program, supports typewriter effect (Linux only) -./main -p model.flm +./main -p ~/Qwen2-7B-Instruct/ # Simple webui, uses streaming output + dynamic batch, supports concurrent access -./webui -p model.flm --port 1234 +./webui -p ~/Qwen2-7B-Instruct/ --port 1234 ``` Compilation on Windows is recommended using Cmake GUI + Visual Studio, completed in the graphical interface. @@ -83,7 +83,7 @@ For compilation issues, especially on Windows, refer to [FAQ](docs/faq.md). ``` python # Model creation from ftllm import llm -model = llm.model("model.flm") +model = llm.model("~/Qwen2-7B-Instruct/") # Generate response print(model.response("你好"))