Qwen
/

Qwen1.5-4B-Chat

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

JustinLin610 commited on Feb 2

Commit

92d2205

•

1 Parent(s): 4cd30db

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -47,10 +47,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 device = "cuda" # the device to load the model onto
 model = AutoModelForCausalLM.from_pretrained(
-    "Qwen2/Qwen2-beta-4B-Chat",
     device_map="auto"
 )
-tokenizer = AutoTokenizer.from_pretrained("Qwen2/Qwen2-beta-4B-Chat")
 prompt = "Give me a short introduction to large language model."
 messages = [

 device = "cuda" # the device to load the model onto
 model = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen2-beta-4B-Chat",
     device_map="auto"
 )
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-beta-4B-Chat")
 prompt = "Give me a short introduction to large language model."
 messages = [