Update models.py

models.py

@@ -105,12 +105,13 @@ class OpenAIModel(BaseTCOModel):
                                            label="($) Price/1K output prompt tokens",
                                            interactive=False
                                            )
-        self.info = gr.Markdown("The cost per input and output tokens values are from OpenAI's pricing web page [here](https://openai.com/pricing)", interactive=False, visible=False)
+        self.info = gr.Markdown("The cost per input and output tokens values are from OpenAI's [pricing web page](https://openai.com/pricing)", interactive=False, visible=False)
         self.model.change(on_model_change, inputs=self.model, outputs=self.context_length).then(define_cost_per_token, inputs=[self.model, self.context_length], outputs=[self.input_tokens_cost_per_second, self.output_tokens_cost_per_second])
         self.context_length.change(define_cost_per_token, inputs=[self.model, self.context_length], outputs=[self.input_tokens_cost_per_second, self.output_tokens_cost_per_second])
         
         self.labor = gr.Number(0, visible=False, 
                                 label="($) Labor cost per month", 
+                                info="This is how much it will cost you to have an engineer specialized in Machine Learning take care of the deployment of your model service",
                                 interactive=True
                                 )
 
@@ -151,10 +152,11 @@ class OpenSourceLlama2Model(BaseTCOModel):
                                            label="($) Price/1K output prompt tokens",
                                            interactive=False
                                            )
-        self.info = gr.Markdown("For the Llama2-70B model, we took the cost per input and output tokens values from the benchmark results [here](https://www.cursor.so/blog/llama-inference#user-content-fn-llama-paper)", interactive=False, visible=False)
+        self.info = gr.Markdown("For the Llama2-70B model, we took the cost per input and output tokens values from [these benchmark results](https://www.cursor.so/blog/llama-inference#user-content-fn-llama-paper)", interactive=False, visible=False)
         
         self.labor = gr.Number(10000, visible=False, 
                                 label="($) Labor cost per month",
+                                info="This is how much it will cost you to have an engineer specialized in Machine Learning take care of the deployment of your model service",
                                 interactive=True
                                 )
         
@@ -195,6 +197,7 @@ class CohereModel(BaseTCOModel):
             
         self.labor = gr.Number(0, visible=False, 
                                 label="($) Labor cost per month", 
+                                info="This is how much it will cost you to have an engineer specialized in Machine Learning take care of the deployment of your model service",
                                 interactive=True
                                 )
 
@@ -268,6 +271,6 @@ class ModelPage:
                 formula = model.get_formula()
                 latency = model.get_latency()
                 
-                return f"Model {current_model} has a cost/request of: ${model_tco}", model_tco, formula, f"The average latency of this model is {latency}", labor_cost
+                return f"Model {current_model} has a cost/request of: ${model_tco:.5f}", model_tco, formula, f"The average latency of this model is {latency}", labor_cost
             
             begin = begin+model_n_args