From 3bb4a3b9d767401eccb50ebbb30a5582e68755bd Mon Sep 17 00:00:00 2001 From: "Yu, Zhentao" Date: Wed, 24 Jan 2024 02:44:29 +0000 Subject: [PATCH] clean example Signed-off-by: Yu, Zhentao --- scripts/python_api_example_for_model_server.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scripts/python_api_example_for_model_server.py b/scripts/python_api_example_for_model_server.py index d4566b0f9..996153b30 100644 --- a/scripts/python_api_example_for_model_server.py +++ b/scripts/python_api_example_for_model_server.py @@ -20,7 +20,7 @@ "I want to learn how to play the piano.", ] -model_name = "/home/zhentao/gpt-j-6b" # "EleutherAI/gpt-j-6b" # model_name from huggingface or local model path +model_name = "EleutherAI/gpt-j-6b" # model_name from huggingface or local model path tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True) res_collect = [] @@ -34,7 +34,7 @@ def f_response(res, working): print(a) print("=====================================") -model_path = "/home/zhentao/ils/ns/q4_j.bin" # please set your corresponding local neural_speed low-bits model file +model_path = "gptj-q4.bin" # please set your corresponding local neural_speed low-bits model file added_count = 0 s = cpp.ModelServer(f_response, # reponse function (deliver generation results and current reamin working size in server) model_path, # model_path