Update app.py

app.py

@@ -12,12 +12,12 @@ theme = gr.themes.Monochrome(
 )
 
 TOKEN = os.getenv("USER_TOKEN")
-instruct_pipeline_3b = pipeline(model="tiiuae/falcon-7b-instruct", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
-instruct_pipeline_7b = pipeline(model="mosesjun0h/llama-7b-hf-baize-lora-bf16", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", use_auth_token=TOKEN)
+instruct_pipeline_falcon = pipeline(model="tiiuae/falcon-7b-instruct", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
+instruct_pipeline_llama = pipeline(model="mosesjun0h/llama-7b-hf-baize-lora-bf16", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", use_auth_token=TOKEN)
 #instruct_pipeline_12b = pipeline(model="databricks/dolly-v2-12b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
 
 def generate(query, temperature, top_p, top_k, max_new_tokens): 
-    return [instruct_pipeline_3b(query, temperature, top_p, top_k, max_new_tokens), instruct_pipeline_7b(query, temperature, top_p, top_k, max_new_tokens)]
+    return [instruct_pipeline_falcon(query, temperature, top_p, top_k, max_new_tokens), instruct_pipeline_llama(query, temperature, top_p, top_k, max_new_tokens)]