diff --git a/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Llama-8B-OrangePi/README.md b/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Llama-8B-OrangePi/README.md index a67174c44db926f34919057fc9308a372f1df2eb..4eeba53977c1b92e0a474a2f59676dbbab516c31 100644 --- a/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Llama-8B-OrangePi/README.md +++ b/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Llama-8B-OrangePi/README.md @@ -210,6 +210,7 @@ python -m examples.run_fa_edge \ --model_path ${权重路径} \ --input_text 'What is deep learning?' \ --max_output_length 20 \ + --is_chat_model \ ``` ## 声明 diff --git a/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Qwen-1.5B-OrangePi/README.md b/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Qwen-1.5B-OrangePi/README.md index c1d8770747114029c86306f5cde922113e755238..8c24269997221c3b6c8f4d83b623550313509534 100644 --- a/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Qwen-1.5B-OrangePi/README.md +++ b/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Qwen-1.5B-OrangePi/README.md @@ -214,7 +214,6 @@ cd $ATB_SPEED_HOME_PATH ``` 执行对话测试 --非量化场景 ```shell python -m examples.run_fa_edge \ --model_path ${权重路径} \ @@ -222,13 +221,6 @@ python -m examples.run_fa_edge \ --max_output_length 20 \ --is_chat_model \ ``` --量化场景 -```shell -python -m examples.run_fa_edge \ - --model_path ${权重路径} \ - --input_text 'What is deep learning?' \ - --max_output_length 20 \ -``` ## 声明 - 本代码仓提到的数据集和模型仅作为示例，这些数据集和模型仅供您用于非商业目的，如您使用这些数据集和模型来完成示例，请您特别注意应遵守对应数据集和模型的License，如您因使用数据集或模型而产生侵权纠纷，华为不承担任何责任。 diff --git a/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Qwen-7B-OrangePi/README.md b/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Qwen-7B-OrangePi/README.md index f22d8534dd60e8d451b8b0766f2d2573f3bc2cc6..d2815475dc8d2689db11a8ab4c05593ab23b0fd3 100644 --- a/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Qwen-7B-OrangePi/README.md +++ b/MindIE/LLM/DeepSeek/DeepSeek-R1-Distill-Qwen-7B-OrangePi/README.md @@ -218,6 +218,7 @@ python -m examples.run_fa_edge \ --model_path ${权重路径} \ --input_text 'What is deep learning?' \ --max_output_length 20 \ + --is_chat_model \ ``` ## 声明