add default values for inference params

app.py

@@ -160,20 +160,20 @@ def pygen_func(nl_code_intent):
     # return str(answer)
     # CT5_URL = "https://api-inference.huggingface.co/models/nielsr/codet5-small-code-summarization-ruby"
 
-def docgen_func(function_code, temp):
-    t = float(temp)
+def docgen_func(function_code, min_length, max_length, top_k, top_p, temp, repetition_penalty):
+    m, M, k, p, t, r = int(min_length), int(max_length), int(top_k), float(top_p/100), float(temp), float(repetition_penalty)
     req_data = {
       "inputs": function_code,
       "parameters": {
-        "min_length": 50,  # (Default: None). Integer to define the minimum length in tokens of the output summary.
-        "max_length": 500, # (Default: None). Integer to define the maximum length in tokens of the output summary.
-        "top_k": 3,        # (Default: None). Integer to define the top tokens considered within the sample operation to create new text.
-        "top_p": 0.8,      # (Default: None). Float to define the tokens that are within the sample` operation of text generation. 
+        "min_length": m,   # (Default: None). Integer to define the minimum length in tokens of the output summary.
+        "max_length": M,   # (Default: None). Integer to define the maximum length in tokens of the output summary.
+        "top_k": k,        # (Default: None). Integer to define the top tokens considered within the sample operation to create new text.
+        "top_p": p,        # (Default: None). Float to define the tokens that are within the sample` operation of text generation. 
                            # Add tokens in the sample for more probable to least probable until the sum of the probabilities is greater than top_p.
         "temperature": t,  # (Default: 1.0). Float (0.0-100.0). The temperature of the sampling operation. 
                            # 1 means regular sampling, 0 means top_k=1, 100.0 is getting closer to uniform probability.
-        "repetition_penalty": 50.0, # (Default: None). Float (0.0-100.0). The more a token is used within generation 
-                                    # the more it is penalized to not be picked in successive generation passes.
+        "repetition_penalty": r, # (Default: None). Float (0.0-100.0). The more a token is used within generation 
+                                 # the more it is penalized to not be picked in successive generation passes.
         "max_time": 80,    # (Default: None). Float (0-120.0). The amount of time in seconds that the query should take maximum. 
                            # Network can cause some overhead so it will be a soft limit.
       },
@@ -195,7 +195,12 @@ iface = gr.Interface(
     [
         # gr.inputs.Textbox(lines=7, label="Code Intent (NL)", default=task_code),
         gr.inputs.Textbox(lines=10, label="Enter Task + Code in Python (PL)", default=task_code), 
-        gr.inputs.Slider(0, 100, label="Temperature"), 
+        gr.inputs.Slider(30, 200, default=100, label="Minimum Length (of the output summary, in tokens)"),
+        gr.inputs.Slider(200, 500, default=350, label="Maximum Length (of the output summary, in tokens)"),
+        gr.inputs.Slider(1, 7, default=3, label="Top K (tokens considered within the sample operation to create new text)"),
+        gr.inputs.Slider(0, 100, default=80, label="Top P (probability threshold for next tokens in sample of new text, cumulative"),
+        gr.inputs.Slider(0, 100, default=1, label="Temperature (of the sampling operation)"),
+        gr.inputs.Slider(0, 100, default=70, label="Repetition Penalty (frequently previously used tokens are downsized)"), 
     ],
     # gr.outputs.Textbox(label="Code Generated PL")) 
     gr.outputs.Textbox(label="Docstring Generated (NL)"),