Update app.py

app.py

@@ -10,8 +10,8 @@ from mamba_ssm.models.mixer_seq_simple import MambaLMHeadModel
 
 device = "cuda"
 tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")
-model = MambaLMHeadModel.from_pretrained("state-spaces/mamba-2.8b", device=device, dtype=torch.float16)
-genlen = 200
+model = MambaLMHeadModel.from_pretrained("state-spaces/mamba-2.8b-slimpj", device=device, dtype=torch.float16)
+genlen = 500
 
 def pred(text_in,):
     tokens = tokenizer(text_in, return_tensors="pt")
@@ -25,8 +25,7 @@ def pred(text_in,):
         return_dict_in_generate=True,
         output_scores=True,
         enable_timing=False,
-        temperature=0.5,
-        top_k=10,
+        temperature=0.7,
         top_p=0.9,
     )
     out = fn()