Update app.py

app.py

@@ -7,108 +7,22 @@ file_name = "mpt-7b-instruct-q5_1-ggjt.bin"
 session_config = SessionConfig(threads=2,batch_size=2)
 model = AutoModel.from_pretrained(repo_name, model_file=file_name, session_config=session_config,verbose=True)
 
-def process_stream(instruction, temperature, top_p, top_k, max_new_tokens, seed):
+def process_stream(instruction):
 
     prompt=f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
 ### Instruction:
 {instruction}
 ### Response:
 Answer:"""
-    generation_config = GenerationConfig(seed=seed,temperature=temperature,top_p=top_p,top_k=top_k,max_new_tokens=max_new_tokens)
+    generation_config = GenerationConfig(seed=1.1,temperature=0.1,top_p=0.15,top_k=0,max_new_tokens=1000)
     response = ""
     streamer = model.stream(prompt=prompt,generation_config=generation_config)
     for new_text in streamer:
         response += new_text
         yield response
+inputs = gr.inputs.Textbox(lines=7, label="Chat with AI")
+outputs = gr.outputs.Textbox(label="Reply")
 
-
-with gr.Blocks(
-    theme=gr.themes.Soft(),
-    css=".disclaimer {font-variant-caps: all-small-caps;}",
-) as demo:
-    with gr.Row():
-        with gr.Column():
-            with gr.Row():
-                instruction = gr.Textbox(
-                    placeholder="Enter your question or instruction here",
-                    label="Question/Instruction",
-                    elem_id="q-input",
-                )
-            with gr.Accordion("Advanced Options:", open=False):
-                with gr.Row():
-                    with gr.Column():
-                        with gr.Row():
-                            temperature = gr.Slider(
-                                label="Temperature",
-                                value=0.8,
-                                minimum=0.1,
-                                maximum=1.0,
-                                step=0.1,
-                                interactive=True,
-                                info="Higher values produce more diverse outputs",
-                            )
-                    with gr.Column():
-                        with gr.Row():
-                            top_p = gr.Slider(
-                                label="Top-p (nucleus sampling)",
-                                value=0.95,
-                                minimum=0.0,
-                                maximum=1.0,
-                                step=0.01,
-                                interactive=True,
-                                info=(
-                                    "Sample from the smallest possible set of tokens whose cumulative probability "
-                                    "exceeds top_p. Set to 1 to disable and sample from all tokens."
-                                ),
-                            )
-                    with gr.Column():
-                        with gr.Row():
-                            top_k = gr.Slider(
-                                label="Top-k",
-                                value=40,
-                                minimum=5,
-                                maximum=80,
-                                step=1,
-                                interactive=True,
-                                info="Sample from a shortlist of top-k tokens — 0 to disable and sample from all tokens.",
-                            )
-                    with gr.Column():
-                        with gr.Row():
-                            max_new_tokens = gr.Slider(
-                                label="Maximum new tokens",
-                                value=256,
-                                minimum=0,
-                                maximum=1024,
-                                step=5,
-                                interactive=True,
-                                info="The maximum number of new tokens to generate",
-                            )
-
-                    with gr.Column():
-                        with gr.Row():
-                            seed = gr.Number(
-                                label="Seed",
-                                value=42,
-                                interactive=True,
-                                info="The seed to use for the generation",
-                                precision=0
-                            )
-    with gr.Row():
-        submit = gr.Button("Submit")
-    with gr.Row():
-        with gr.Box():
-            gr.Markdown("**Output:**")
-            output_7b = gr.Markdown() 
-
-    submit.click(
-        process_stream,
-        inputs=[instruction, temperature, top_p, top_k, max_new_tokens,seed],
-        outputs=output_7b,
-    )
-    instruction.submit(
-        process_stream,
-        inputs=[instruction, temperature, top_p, top_k, max_new_tokens,seed],
-        outputs=output_7b,
-    )
-
-demo.queue(max_size=4, concurrency_count=1).launch(debug=True)
+gr.Interface(fn=process_stream, inputs=inputs, outputs=outputs, title="Self_Trained_V2",
+             description="Ask anything you want",
+             ).launch(share=True)