Llama-3.2-3B-Instruct

Paused

Nymbo commited on Oct 2

Commit

9728c87

•

1 Parent(s): 6f1aebd

removing zerogpu

Files changed (1) hide show

app.py CHANGED Viewed

@@ -1,6 +1,6 @@
 import os
 import time
-import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer, BitsAndBytesConfig
 import gradio as gr
@@ -46,7 +46,7 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto",
     quantization_config=quantization_config)
-@spaces.GPU()
 def stream_chat(
     message: str,
     history: list,

 import os
 import time
+# import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer, BitsAndBytesConfig
 import gradio as gr
     device_map="auto",
     quantization_config=quantization_config)
+# @spaces.GPU()
 def stream_chat(
     message: str,
     history: list,