Update app.py

app.py

@@ -1,3 +1,4 @@
+import spaces 
 import os, copy
 os.environ["RWKV_V7_ON"] = '1'
 os.environ["RWKV_JIT_ON"] = '1'
@@ -19,7 +20,7 @@ gpu_h = nvmlDeviceGetHandleByIndex(0)
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 ctx_limit = 4000
-gen_limit = 1500
+gen_limit = 32000
 
 ########################## text rwkv ################################################################
 from rwkv.utils import PIPELINE, PIPELINE_ARGS
@@ -32,7 +33,7 @@ pipeline_v6 = PIPELINE(model_v6, "rwkv_vocab_v20230424")
 args = model_v6.args
 
 penalty_decay = 0.996
-
+@spaces.GPU()
 def generate_prompt(instruction, input=""):
     instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
     input = input.strip().replace('\r\n','\n').replace('\n\n','\n')