From ffc3496306854e47fe2a45e946c88c3d4403e103 Mon Sep 17 00:00:00 2001 From: Yang An Date: Fri, 4 Aug 2023 15:44:26 +0800 Subject: [PATCH] Update quickusage in Chinese --- README_CN.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README_CN.md b/README_CN.md index f2c4e01..334c9c5 100644 --- a/README_CN.md +++ b/README_CN.md @@ -86,6 +86,8 @@ tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, bf16=True).eval() ## 打开fp16精度，V100、P100、T4等显卡建议启用以节省显存 # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, fp16=True).eval() +## 使用CPU进行推理，需要约32GB内存 +# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="cpu", trust_remote_code=True).eval() # 默认使用fp32精度 model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval() model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参 @@ -124,6 +126,8 @@ tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, bf16=True).eval() ## 打开fp16精度，V100、P100、T4等显卡建议启用以节省显存 # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, fp16=True).eval() +## 使用CPU进行推理，需要约32GB内存 +# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="cpu", trust_remote_code=True).eval() # 默认使用fp32精度 model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True).eval() model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参