update

app.py

@@ -49,9 +49,13 @@ def text_generate(problem, template, prompt):
             {
             "top_p": 0.9,
           "temperature": 1.1,
-          "max_new_tokens": 250,
-          "return_full_text": True
-          }}
+          #"max_new_tokens": 250,
+          "return_full_text": False
+          }, "options": 
+              {
+              "use_cache": True,
+              "wait_for_model":True
+              }}
   response = requests.post(API_URL, headers=headers, json=json_)
   print(f"Response  is : {response}")
   output = response.json()
@@ -69,7 +73,7 @@ demo = gr.Blocks()
 with demo:
   gr.Markdown("<h1><center>Step By Step With Bloom</center></h1>")
   gr.Markdown(
-        """ APOLOGIES WIP FIXING SOMETHING. [BigScienceW Bloom](https://twitter.com/BigscienceW) \n\n Large language models have demonstrated a capability of 'Chain-of-thought reasoning'. A group of amazing researchers( [Jason Wei et al.](https://arxiv.org/abs/2205.11916)) recently found out that by adding **Lets think step by step** it improves the model's zero-shot performance. Some might say — You can get good results out of LLMs if you know how to speak to them. This space is an attempt at inspecting this LLM behavior/capability in the new HuggingFace BigScienceW [Bloom](https://huggingface.co/bigscience/bloom) model. \n\nThis Space is created by [Yuvraj Sharma](https://twitter.com/yvrjsharma) for EuroPython 2022 Demo.\nThis Space might sometime fail due to inference queue being full and logs would end up showing error as *queue full, try again later*, don't despair and try again after some time. I would try and improve the app as well over next couple days."""
+        """[BigScienceW Bloom](https://twitter.com/BigscienceW) \n\n Large language models have demonstrated a capability of 'Chain-of-thought reasoning'. A group of amazing researchers( [Jason Wei et al.](https://arxiv.org/abs/2205.11916)) recently found out that by adding **Lets think step by step** it improves the model's zero-shot performance. Some might say — You can get good results out of LLMs if you know how to speak to them. This space is an attempt at inspecting this LLM behavior/capability in the new HuggingFace BigScienceW [Bloom](https://huggingface.co/bigscience/bloom) model. \n\nThis Space is created by [Yuvraj Sharma](https://twitter.com/yvrjsharma) for EuroPython 2022 Demo.\nThis Space might sometime fail due to inference queue being full and logs would end up showing error as *queue full, try again later*, don't despair and try again after some time. I would try and improve the app as well over next couple days."""
         )
   with gr.Row():