Spaces:

dasomaru
/

gemma

Runtime error

dasomaru commited on Apr 28

Commit

5267417

verified ·

1 Parent(s): 576739c

Update generator/llm_inference.py

Files changed (1) hide show

generator/llm_inference.py CHANGED Viewed

@@ -7,7 +7,7 @@ generator = pipeline(
     model="dasomaru/gemma-3-4bit-it-demo",  # 네가 업로드한 모델 이름
     tokenizer="dasomaru/gemma-3-4bit-it-demo",
     device=0,  # CUDA:0 사용 (GPU). CPU만 있으면 device=-1
-    max_new_tokens=512,
     temperature=0.7,
     top_p=0.9,
     repetition_penalty=1.1

     model="dasomaru/gemma-3-4bit-it-demo",  # 네가 업로드한 모델 이름
     tokenizer="dasomaru/gemma-3-4bit-it-demo",
     device=0,  # CUDA:0 사용 (GPU). CPU만 있으면 device=-1
+    max_new_tokens=2048,
     temperature=0.7,
     top_p=0.9,
     repetition_penalty=1.1