Spaces:

izumi-lab
/

llama-13b-japanese-lora-v0-1ep

Paused

retarfi commited on May 23, 2023

Commit

5b34bc3

•

1 Parent(s): f2582eb

fix: typo

Files changed (1) hide show

app.py CHANGED Viewed

@@ -250,10 +250,10 @@ description = (
     "It is a 13B-parameter LLaMA model finetuned to follow instructions.  "
     "It is trained on the [izumi-lab/llm-japanese-dataset](https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset) dataset.  "
     "For more information, please visit [the project's website](https://llm.msuzuki.me).  "
-    "This model can output up to 256 tokens, but the maximum number of tokens is 227 due to the GPU memory limit of HuggingFace Space. "
     "It takes about **1 minute** to output. When access is concentrated, the operation may become slow."
 )
-with gr.Blocks()
     css="""#col_container { margin-left: auto; margin-right: auto;}""",
     theme=theme,
 ) as demo:

     "It is a 13B-parameter LLaMA model finetuned to follow instructions.  "
     "It is trained on the [izumi-lab/llm-japanese-dataset](https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset) dataset.  "
     "For more information, please visit [the project's website](https://llm.msuzuki.me).  "
+    "This model can output up to 256 tokens, but the maximum number of tokens is 227 due to the GPU memory limit of HuggingFace Space.  "
     "It takes about **1 minute** to output. When access is concentrated, the operation may become slow."
 )
+with gr.Blocks(
     css="""#col_container { margin-left: auto; margin-right: auto;}""",
     theme=theme,
 ) as demo: