Upload 2 files

app.py

@@ -0,0 +1,165 @@
+import os
+
+import gradio as gr
+from text_generation import Client
+
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
+API_URL = " https://api-inference.huggingface.co/models/BigCode/octocoder"
+
+theme = gr.themes.Monochrome(
+    primary_hue="indigo",
+    secondary_hue="blue",
+    neutral_hue="slate",
+    radius_size=gr.themes.sizes.radius_sm,
+    font=[
+        gr.themes.GoogleFont("Open Sans"),
+        "ui-sans-serif",
+        "system-ui",
+        "sans-serif",
+    ],
+)
+
+client = Client(
+    API_URL,
+    headers={"Authorization": f"Bearer {HF_TOKEN}"},
+)
+
+def generate(query:str, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0, ):
+    if query.endswith("."):
+        prompt = f"Question: {query}\n\nAnswer:"
+    else:
+        prompt = f"Question: {query}.\n\nAnswer:"
+
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
+
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
+    )
+
+    stream = client.generate_stream(prompt, **generate_kwargs)
+    output = ""
+
+    previous_token = ""
+    for response in stream:
+        if response.token.text == "<|endoftext|>":
+            return output
+        else:
+            output += response.token.text
+        previous_token = response.token.text
+        yield output
+    return output
+
+
+def process_example(args):
+    for x in generate(args):
+        pass
+    return x
+
+
+css = ".generating {visibility: hidden}"
+
+monospace_css = """
+#q-input textarea {
+    font-family: monospace, 'Consolas', Courier, monospace;
+}
+"""
+
+description = """
+<div style="text-align: center;">
+    <center><img src='https://raw.githubusercontent.com/bigcode-project/octopack/31f3320f098703c7910e43492c39366eeea68d83/banner.png' width='70%'/></center>
+    <br>
+    <h1><u> OctoCoder Demo </u></h1>
+</div>
+<br>
+<div style="text-align: center;">
+    <p>This is a demo to demonstrate the capabilities of <a href="https://huggingface.co/bigcode/octocoder">OctoCoder</a> model by showing how it can be used to generate code by following the instructions provided in the input.</p>
+    <p><strong>OctoCoder</strong> is an instruction tuned model with 15.5B parameters created by finetuning StarCoder on CommitPackFT & OASST</p>
+</div>
+"""
+disclaimer = """⚠️<b>Any use or sharing of this demo constitues your acceptance of the BigCode [OpenRAIL-M](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) License Agreement and the use restrictions included within.</b>\
+ <br>**Intended Use**: this app and its [supporting model](https://huggingface.co/bigcode) are provided for demonstration purposes; not to serve as replacement for human expertise. For more details on the model's limitations in terms of factuality and biases, see the [model card.](https://huggingface.co/bigcode)"""
+
+
+examples = [['Please write a function in Python that performs bubble sort.']]
+
+
+with gr.Blocks(theme=theme, analytics_enabled=False, css=css) as demo:
+    with gr.Column():
+        gr.Markdown(description)
+        with gr.Row():
+            with gr.Column():
+                with gr.Accordion("Settings", open=True):
+                    with gr.Row():
+                        column_1, column_2 = gr.Column(), gr.Column()
+                        with column_1:
+                            temperature = gr.Slider(
+                                label="Temperature",
+                                value=0.2,
+                                minimum=0.0,
+                                maximum=1.0,
+                                step=0.05,
+                                interactive=True,
+                                info="Higher values produce more diverse outputs",
+                            )
+                            max_new_tokens = gr.Slider(
+                                label="Max new tokens",
+                                value=256,
+                                minimum=0,
+                                maximum=8192,
+                                step=64,
+                                interactive=True,
+                                info="The maximum numbers of new tokens",
+                            )
+                        with column_2:
+                            top_p = gr.Slider(
+                                label="Top-p (nucleus sampling)",
+                                value=0.90,
+                                minimum=0.0,
+                                maximum=1,
+                                step=0.05,
+                                interactive=True,
+                                info="Higher values sample more low-probability tokens",
+                            )
+                            repetition_penalty = gr.Slider(
+                                label="Repetition penalty",
+                                value=1.2,
+                                minimum=1.0,
+                                maximum=2.0,
+                                step=0.05,
+                                interactive=True,
+                                info="Penalize repeated tokens",
+                            )
+
+        with gr.Row():
+            with gr.Column():
+                instruction = gr.Textbox(
+                    placeholder="Enter your query here",
+                    lines=5,
+                    label="Input",
+                    elem_id="q-input",
+                )
+                submit = gr.Button("Generate", variant="primary")
+                output = gr.Code(elem_id="q-output", lines=30, label="Output")
+                gr.Markdown(disclaimer)
+                gr.Examples(
+                    examples=examples,
+                    inputs=[instruction],
+                    cache_examples=False,
+                    fn=process_example,
+                    outputs=[output],
+                )
+
+    submit.click(
+        generate,
+        inputs=[instruction, temperature, max_new_tokens, top_p, repetition_penalty],
+        outputs=[output],
+    )
+demo.queue(concurrency_count=16).launch(debug=True)

requirements.txt

@@ -0,0 +1,71 @@
+aiofiles==23.2.1
+aiohttp==3.8.5
+aiosignal==1.3.1
+altair==5.0.1
+annotated-types==0.5.0
+anyio==3.7.1
+async-timeout==4.0.2
+attrs==23.1.0
+certifi==2023.7.22
+charset-normalizer==3.2.0
+click==8.1.6
+contourpy==1.1.0
+cycler==0.11.0
+exceptiongroup==1.1.2
+fastapi==0.101.0
+ffmpy==0.3.1
+filelock==3.12.2
+fonttools==4.42.0
+frozenlist==1.4.0
+fsspec==2023.6.0
+gradio==3.39.0
+gradio_client==0.3.0
+h11==0.14.0
+httpcore==0.17.3
+httpx==0.24.1
+huggingface-hub==0.16.4
+idna==3.4
+importlib-resources==6.0.1
+Jinja2==3.1.2
+jsonschema==4.19.0
+jsonschema-specifications==2023.7.1
+kiwisolver==1.4.4
+linkify-it-py==2.0.2
+markdown-it-py==2.2.0
+MarkupSafe==2.1.3
+matplotlib==3.7.2
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+multidict==6.0.4
+numpy==1.24.4
+orjson==3.9.4
+packaging==23.1
+pandas==2.0.3
+Pillow==10.0.0
+pkgutil_resolve_name==1.3.10
+pydantic==1.10.12
+pydantic_core==2.4.0
+pydub==0.25.1
+pyparsing==3.0.9
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytz==2023.3
+PyYAML==6.0.1
+referencing==0.30.2
+requests==2.31.0
+rpds-py==0.9.2
+semantic-version==2.10.0
+six==1.16.0
+sniffio==1.3.0
+starlette==0.27.0
+text-generation==0.6.0
+toolz==0.12.0
+tqdm==4.66.0
+typing_extensions==4.7.1
+tzdata==2023.3
+uc-micro-py==1.0.2
+urllib3==2.0.4
+uvicorn==0.23.2
+websockets==11.0.3
+yarl==1.9.2
+zipp==3.16.2