instruction response pair

app.py

@@ -6,7 +6,6 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-# client = InferenceClient("BatsResearch/bonito-v1")
 model = AutoModelForCausalLM.from_pretrained("BatsResearch/bonito-v1")
 tokenizer = AutoTokenizer.from_pretrained("BatsResearch/bonito-v1")
 model.to("cuda")
@@ -31,49 +30,22 @@ def respond(
         top_p=top_p,
         do_sample=True,
     )
+    pred_start = int(input_ids.shape[-1])
 
-    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    response = tokenizer.decode(output[0][pred_start:], skip_special_tokens=True)
 
-    # response = client.text_generation(input_text, max_new_tokens=max_tokens, temperature=temperature, top_p=top_p)
+    # check if <|pipe|> is in the response
+    if "<|pipe|>" in response:
+        pair = response.split("<|pipe|>")
+        instruction = pair[0].strip().replace("{{context}}", message)
+        response = pair[1].strip()
+    else:
+        # fallback
+        instruction = pair[0].strip().replace("{{context}}", message)
+        response = "Unable to generate response. Please regenerate."
 
-    return response
-    # messages = []
-    # messages.append({"role": "user", "content": message})
+    return instruction, response
 
-    # response = ""
-
-
-    # for message in client.text_generation(
-    #     messages,
-    #     max_tokens=max_tokens,
-    #     stream=True,
-    #     temperature=temperature,
-    #     top_p=top_p,
-    # ):
-    #     token = message.choices[0].delta.content
-
-    #     response += token
-    #     yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-# demo = gr.ChatInterface(
-#     respond,
-#     additional_inputs=[
-#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-#         gr.Slider(
-#             minimum=0.1,
-#             maximum=1.0,
-#             value=0.95,
-#             step=0.05,
-#             label="Top-p (nucleus sampling)",
-#         ),
-#     ],
-# )
 task_types = [
     "extractive question answering",
     "multiple-choice question answering",
@@ -101,7 +73,7 @@ demo = gr.Interface(
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Dropdown(task_types, label="Task type"),
     ],
-    outputs=gr.Textbox(label="Response"),
+    outputs=[gr.Textbox(label="Input"), gr.Textbox(label="Output")],
     additional_inputs=[
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),