upload stable application and requirements file

app.py

@@ -0,0 +1,202 @@
+import os
+import gradio as gr
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+
+# initialize the model
+model_name = 'anugrahap/gpt2-indo-textgen'
+
+# define the tokenization method
+tokenizer = AutoTokenizer.from_pretrained(model_name,
+                                          model_max_length=1e30,
+                                          padding_side='right',
+                                          return_tensors='pt')
+
+# add the EOS token as PAD token to avoid warnings
+model = AutoModelForCausalLM.from_pretrained(model_name, pad_token_id=tokenizer.eos_token_id)
+
+generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
+
+# create the decoder parameter to generate the text
+def single_generation(text,min_length,max_length,temperature,top_k,top_p,num_beams,repetition_penalty,do_sample):
+    # create local variable for error parameter    
+    error_rep=ValueError(f"ERROR: repetition penalty cannot be lower than one! Given rep penalty = {repetition_penalty}")
+    error_temp=ValueError(f"ERROR: temperature cannot be zero or lower! Given temperature = {temperature}")
+    error_minmax=ValueError(f"ERROR: min length must be lower than or equal to max length! Given min length = {min_length}")
+    error_numbeams_type=TypeError(f"ERROR: number of beams must be an integer not {type(num_beams)}")
+    error_topk_type=TypeError(f"ERROR: top k must be an integer not {type(top_k)}")
+    error_minmax_type=TypeError(f"ERROR: min length and max length must be an integer not {type(min_length)} and {type(max_length)}")   
+    error_empty=ValueError("ERROR: Input Text cannot be empty!")
+    error_unknown=TypeError("Unknown Error.")
+
+    if text != '':
+        if type(min_length) == int and type(max_length) == int:
+            if type(top_k) == int:
+                if type(num_beams) == int:
+                    if min_length <= max_length:
+                        if temperature > 0:
+                            if repetition_penalty >= 1:
+                                result = generator(text,
+                                                   min_length=min_length,
+                                                   max_length=max_length,
+                                                   temperature=temperature,
+                                                   top_k=top_k,
+                                                   top_p=top_p,
+                                                   num_beams=num_beams,
+                                                   repetition_penalty=repetition_penalty,
+                                                   do_sample=do_sample,
+                                                   no_repeat_ngram_size=2,
+                                                   num_return_sequences=1)
+                                return result[0]["generated_text"]
+                            elif repetition_penalty < 1:
+                                return error_rep
+                        elif temperature <= 0:
+                            return error_temp
+                    elif min_length > max_length:
+                        return error_minmax
+                elif type(num_beams) != int:
+                    return error_numbeams_type
+            elif type(top_k) != int:
+                return error_topk_type
+        elif type(min_length) != int or type(max_length) != int:
+            return error_minmax_type  
+    elif text == '':
+        return error_empty
+    else:
+        return error_unknown
+
+# create the decoder parameter to generate the text
+def multiple_generation(text,min_length,max_length,temperature,top_k,top_p,num_beams,repetition_penalty,do_sample):
+    # create local variable for error parameter    
+    error_rep=ValueError(f"ERROR: repetition penalty cannot be lower than one! Given rep penalty = {repetition_penalty}")
+    error_temp=ValueError(f"ERROR: temperature cannot be zero or lower! Given temperature = {temperature}")
+    error_minmax=ValueError(f"ERROR: min length must be lower than or equal to max length! Given min length = {min_length}")
+    error_numbeams_type=TypeError(f"ERROR: number of beams must be an integer not {type(num_beams)}")
+    error_topk_type=TypeError(f"ERROR: top k must be an integer not {type(top_k)}")
+    error_minmax_type=TypeError(f"ERROR: min length and max length must be an integer not {type(min_length)} and {type(max_length)}")   
+    error_empty=ValueError("ERROR: Input Text cannot be empty!")
+    error_unknown=TypeError("Unknown Error.")
+
+    if text != '':
+        if type(min_length) == int and type(max_length) == int:
+            if type(top_k) == int:
+                if type(num_beams) == int:
+                    if min_length <= max_length:
+                        if temperature > 0:
+                            if repetition_penalty >= 1:
+                                result = generator(text,
+                                                   min_length=min_length,
+                                                   max_length=max_length,
+                                                   temperature=temperature,
+                                                   top_k=top_k,
+                                                   top_p=top_p,
+                                                   num_beams=num_beams,
+                                                   repetition_penalty=repetition_penalty,
+                                                   do_sample=do_sample,
+                                                   no_repeat_ngram_size=2,
+                                                   num_return_sequences=3)
+                                return result[0]["generated_text"], result[1]["generated_text"], result[2]["generated_text"],
+                            elif repetition_penalty < 1:
+                                return error_rep,error_rep,error_rep
+                        elif temperature <= 0:
+                            return error_temp,error_temp,error_temp
+                    elif min_length > max_length:
+                        return error_minmax,error_minmax,error_minmax
+                elif type(num_beams) != int:
+                    return error_numbeams_type,error_numbeams_type,error_numbeams_type
+            elif type(top_k) != int:
+                return error_topk_type,error_topk_type,error_topk_type
+        elif type(min_length) != int or type(max_length) != int:
+            return  error_minmax_type,error_minmax_type,error_minmax_type
+    elif text == '':
+        return error_empty,error_empty,error_empty
+    else:
+        return error_unknown,error_unknown,error_unknown
+
+
+# create the baseline examples
+examples = [
+    ["Indonesia adalah negara kepulauan", 10, 30, 1.0, 25, 0.92, 5, 2.0, True],
+    ["Indonesia adalah negara kepulauan", 10, 30, 1.0, 25, 0.92, 5, 1.0, False],
+    ["Skripsi merupakan tugas akhir mahasiswa", 20, 40, 1.0, 50, 0.92, 1, 2.0, True],
+    ["Skripsi merupakan tugas akhir mahasiswa", 20, 40, 1.0, 50, 0.92, 1, 1.0, False],
+    ["Pemandangan di pantai kuta Bali sangatlah indah.", 30, 50, 0.5, 40, 0.98, 10, 1.0, True],
+    ["Pemandangan di pantai kuta Bali sangatlah indah.", 10, 30, 1.5, 30, 0.93, 5, 2.0, True]]
+
+# using gradio block to create the interface
+with gr.Blocks(title="GPT-2 Indonesian Text Generation Playground", theme='Default') as app:
+    gr.Markdown("""
+    <style>
+    .center {
+    display: block;
+    margin-top: 20px;
+    margin-down: 0px;
+    margin-left: auto;
+    margin-right: auto;
+    }
+    </style>
+    <style>
+    h1 {
+    text-align: center;
+    margin-top: 0px;
+    }
+    </style>
+    <img src="https://iili.io/HayCG44.md.png"
+    alt="Q-GEN Logo"
+    border="0" 
+    class="center"
+    style="height: 100px; width: 100px;"/>
+    <h1>GPT-2 Indonesian Text Generation Playground</h1>""")
+
+    gr.Markdown("<p><i>This project is a part of thesis requirement of Anugrah Akbar Praramadhan</i></p>")
+
+    with gr.Tabs():
+        #single generation
+        with gr.TabItem("Single Generation"):
+            with gr.Row():
+                with gr.Column():
+                    input1=[gr.Textbox(lines=5, label="Input Text"),
+                           gr.Slider(label="Min Length", minimum=10, maximum=50, value=10, step=5),
+                           gr.Slider(label="Max Length", minimum=10, maximum=100, value=30, step=10),
+                           gr.Number(label="Temperature Sampling", value=1.5),
+                           gr.Slider(label="Top K Sampling", minimum=0, maximum=100, value=30, step=5),
+                           gr.Slider(label="Top P Sampling", minimum=0.01, maximum=1, value=0.93),
+                           gr.Slider(label="Number of Beams", minimum=1, maximum=10, value=5, step=1),
+                           gr.Number(label="Rep Penalty", value=2.0),
+                           gr.Dropdown(label="Do Sample?", choices=[True,False], value=True, multiselect=False)]
+
+                with gr.Column():
+                    output1=gr.Textbox(lines=5, max_lines=50, label="Generated Text with Greedy/Beam Search Decoding")
+                    button1=gr.Button("Run the model")
+                    button1.click(fn=single_generation, inputs=input1, outputs=output1, show_progress=True)
+            gr.Examples(examples, inputs=input1)
+
+        #multiple generation
+        with gr.TabItem("Multiple Generation"):
+            with gr.Row():
+                with gr.Column():
+                    input2=[gr.Textbox(lines=5, label="Input Text"),
+                            gr.Slider(label="Min Length", minimum=10, maximum=50, value=10, step=5),
+                            gr.Slider(label="Max Length", minimum=10, maximum=100, value=30, step=10),
+                            gr.Number(label="Temperature Sampling", value=1.5),
+                            gr.Slider(label="Top K Sampling", minimum=0, maximum=100, value=30, step=5),
+                            gr.Slider(label="Top P Sampling", minimum=0.01, maximum=1, value=0.93),
+                            gr.Slider(label="Number of Beams", minimum=1, maximum=10, value=5, step=1),
+                            gr.Number(label="Rep Penalty", value=2.0),
+                            gr.Dropdown(label="Do Sample?", choices=[True,False], value=True, multiselect=False)]
+                with gr.Column():
+                    output2=[gr.Textbox(lines=5, max_lines=50, label="#1 Generated Text with Greedy/Beam Search Decoding"),
+                            gr.Textbox(lines=5, max_lines=50, label="#2 Generated Text with Greedy/Beam Search Decoding"),
+                            gr.Textbox(lines=5, max_lines=50, label="#3 Generated Text with Greedy/Beam Search Decoding")]
+                    button2=gr.Button("Run the model")
+                    button2.click(fn=multiple_generation, inputs=input2, outputs=output2, show_progress=True)
+            gr.Examples(examples, inputs=input2)
+    
+    gr.Markdown("""<p style='text-align: center'>Copyright Anugrah Akbar Praramadhan 2023 <br>
+    <p style='text-align: center'> Trained on Indo4B Benchmark Dataset of Indonesian language Wikipedia with a Causal Language Modeling (CLM) objective <br>
+    <p style='text-align: center'><a href='https://huggingface.co/anugrahap/gpt2-indo-textgen' target='_blank'>Link to the Trained Model</a><br>
+    <p style='text-align: center'><a href='https://huggingface.co/spaces/anugrahap/gpt2-indo-textgen/tree/main' target='_blank'>Link to the Project Repository</a><br>
+    <p style='text-align: center'><a href='https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf' target='_blank'>Original Paper</a>
+    """)
+
+if __name__=='__main__':
+    app.launch()

requirements.txt

@@ -0,0 +1,7 @@
+gradio==3.16.1
+huggingface-hub==0.11.1
+protobuf==3.19.6
+torch==1.12.1
+torchaudio==0.12.1
+torchvision==0.13.1
+transformers==4.25.1