Update app.py

app.py

@@ -12,7 +12,7 @@ REPO_NAME = 'schuler/experimental-JP47D21-KPhi-3-micro-4k-instruct'
 def load_model(repo_name):
     tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
     generator_conf = GenerationConfig.from_pretrained(repo_name)
-    model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True, torch_dtype=torch.bfloat16)
+    model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True, torch_dtype=torch.bfloat16, attn_implementation="eager")
     model.to('cuda')
     return tokenizer, generator_conf, model