kfkas
/

Llama-2-ko-7b-Chat

Text Generation

llama-2-ko-chat

text-generation-inference

Model card Files Files and versions Community

kfkas commited on Jul 27, 2023

Commit

10e74b2

•

1 Parent(s): eb2932d

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -68,7 +68,7 @@ def gen(x, model, tokenizer, device):
         max_new_tokens=1024,
         early_stopping=True,
         do_sample=True,
-        top_k=10,
         top_p=0.92,
         no_repeat_ngram_size=3,
         eos_token_id=2,
@@ -95,7 +95,7 @@ def LLM_infer(input):
 if __name__ == "__main__":
-    text = LLM_infer("살인죄를 알려줘")
     print(text)
 ```

         max_new_tokens=1024,
         early_stopping=True,
         do_sample=True,
+        top_k=20,
         top_p=0.92,
         no_repeat_ngram_size=3,
         eos_token_id=2,
 if __name__ == "__main__":
+    text = LLM_infer("삼원색에 대해 알려줘")
     print(text)
 ```