shenzhi-wang
/

Llama3-8B-Chinese-Chat

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

shenzhi-wang commited on Apr 24

Commit

dbfbe5c

•

1 Parent(s): 0fcc2d2

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -115,7 +115,7 @@ input_ids = tokenizer.apply_chat_template(
 outputs = model.generate(
     input_ids,
-    max_new_tokens=1024,
     do_sample=True,
     temperature=0.6,
     top_p=0.9,

 outputs = model.generate(
     input_ids,
+    max_new_tokens=8196,
     do_sample=True,
     temperature=0.6,
     top_p=0.9,