Add files

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

app.py

@@ -0,0 +1,215 @@
+import argparse
+import os
+
+import gradio as gr
+from text_generation import Client
+
+TITLE = """<h2 align="center">🚀 Falcon-Chat demo</h2>"""
+USER_NAME = "User"
+BOT_NAME = "Falcon"
+DEFAULT_INSTRUCTIONS = f"""The following is a conversation between a highly knowledgeable and intelligent AI assistant, called Falcon, and a human user, called User. In the following interactions, User and Falcon will converse in natural language, and Falcon will answer User's questions. Falcon was built to be respectful, polite and inclusive. Falcon was built by the Technology Innovation Institute in Abu Dhabi. Falcon will never decline to answer a question, and always attempts to give an answer that User would be satisfied with. It knows a lot, and always tells the truth. The conversation begins.
+"""
+RETRY_COMMAND = "/retry"
+STOP_STR = f"\n{USER_NAME}:"
+STOP_SUSPECT_LIST = [":", "\n", "User"]
+
+INFERENCE_ENDPOINT = os.environ.get("INFERENCE_ENDPOINT")
+INFERENCE_AUTH = os.environ.get("INFERENCE_AUTH")
+
+
+def chat_accordion():
+    with gr.Accordion("Parameters", open=False):
+        temperature = gr.Slider(
+            minimum=0.1,
+            maximum=2.0,
+            value=0.8,
+            step=0.1,
+            interactive=True,
+            label="Temperature",
+        )
+        top_p = gr.Slider(
+            minimum=0.1,
+            maximum=0.99,
+            value=0.9,
+            step=0.01,
+            interactive=True,
+            label="p (nucleus sampling)",
+        )
+    return temperature, top_p
+
+
+def format_chat_prompt(message: str, chat_history, instructions: str) -> str:
+    instructions = instructions.strip(" ").strip("\n")
+    prompt = instructions
+    for turn in chat_history:
+        user_message, bot_message = turn
+        prompt = f"{prompt}\n{USER_NAME}: {user_message}\n{BOT_NAME}: {bot_message}"
+    prompt = f"{prompt}\n{USER_NAME}: {message}\n{BOT_NAME}:"
+    return prompt
+
+
+def chat(client: Client):
+    with gr.Column(elem_id="chat_container"):
+        with gr.Row():
+            chatbot = gr.Chatbot(elem_id="chatbot")
+        with gr.Row():
+            inputs = gr.Textbox(
+                placeholder=f"Hello {BOT_NAME} !!",
+                label="Type an input and press Enter",
+                max_lines=3,
+            )
+
+    with gr.Row(elem_id="button_container"):
+        with gr.Column():
+            retry_button = gr.Button("♻️ Retry last turn")
+        with gr.Column():
+            delete_turn_button = gr.Button("🧽 Delete last turn")
+        with gr.Column():
+            clear_chat_button = gr.Button("✨ Delete all history")
+
+    gr.Examples(
+        [
+            ["Hey Falcon! Any recommendations for my holidays in Abu Dhabi?"],
+            ["What's the Everett interpretation of quantum mechanics?"],
+            ["Give me a list of the top 10 dive sites you would recommend around the world."],
+            ["Can you tell me more about deep-water soloing?"],
+            ["Can you write a short tweet about the Apache 2.0 release of our latest AI model, Falcon LLM?"],
+        ],
+        inputs=inputs,
+        label="Click on any example and press Enter in the input textbox!",
+    )
+
+    with gr.Row(elem_id="param_container"):
+        with gr.Column():
+            temperature, top_p = chat_accordion()
+        with gr.Column():
+            with gr.Accordion("Instructions", open=False):
+                instructions = gr.Textbox(
+                    placeholder="LLM instructions",
+                    value=DEFAULT_INSTRUCTIONS,
+                    lines=10,
+                    interactive=True,
+                    label="Instructions",
+                    max_lines=16,
+                    show_label=False,
+                )
+
+    def run_chat(message: str, chat_history, instructions: str, temperature: float, top_p: float):
+        if not message or (message == RETRY_COMMAND and len(chat_history) == 0):
+            yield chat_history
+            return
+
+        if message == RETRY_COMMAND and chat_history:
+            prev_turn = chat_history.pop(-1)
+            user_message, _ = prev_turn
+            message = user_message
+
+        prompt = format_chat_prompt(message, chat_history, instructions)
+        chat_history = chat_history + [[message, ""]]
+        stream = client.generate_stream(
+            prompt,
+            do_sample=True,
+            max_new_tokens=1024,
+            stop_sequences=[STOP_STR, "<|endoftext|>"],
+            temperature=temperature,
+            top_p=top_p,
+        )
+        acc_text = ""
+        for idx, response in enumerate(stream):
+            text_token = response.token.text
+
+            if response.details:
+                return
+
+            if text_token in STOP_SUSPECT_LIST:
+                acc_text += text_token
+                continue
+
+            if idx == 0 and text_token.startswith(" "):
+                text_token = text_token[1:]
+
+            acc_text += text_token
+            last_turn = list(chat_history.pop(-1))
+            last_turn[-1] += acc_text
+            chat_history = chat_history + [last_turn]
+            yield chat_history
+            acc_text = ""
+
+    def delete_last_turn(chat_history):
+        if chat_history:
+            chat_history.pop(-1)
+        return {chatbot: gr.update(value=chat_history)}
+
+    def run_retry(message: str, chat_history, instructions: str, temperature: float, top_p: float):
+        yield from run_chat(RETRY_COMMAND, chat_history, instructions, temperature, top_p)
+
+    def clear_chat():
+        return []
+
+    inputs.submit(
+        run_chat,
+        [inputs, chatbot, instructions, temperature, top_p],
+        outputs=[chatbot],
+        show_progress=False,
+    )
+    inputs.submit(lambda: "", inputs=None, outputs=inputs)
+    delete_turn_button.click(delete_last_turn, inputs=[chatbot], outputs=[chatbot])
+    retry_button.click(
+        run_retry,
+        [inputs, chatbot, instructions, temperature, top_p],
+        outputs=[chatbot],
+        show_progress=False,
+    )
+    clear_chat_button.click(clear_chat, [], chatbot)
+
+
+def get_demo(client: Client):
+    with gr.Blocks(
+        # css=None
+        # css="""#chat_container {width: 700px; margin-left: auto; margin-right: auto;}
+        #        #button_container {width: 700px; margin-left: auto; margin-right: auto;}
+        #        #param_container {width: 700px; margin-left: auto; margin-right: auto;}"""
+        css="""#chatbot {
+    font-size: 14px;
+    min-height: 300px;
+}"""
+    ) as demo:
+        gr.HTML(TITLE)
+
+        with gr.Row():
+            # with gr.Column():
+            #     gr.Image("home-banner.jpg", elem_id="banner-image", show_label=False)
+            with gr.Column():
+                gr.Markdown(
+                    """**Chat with [Falcon-40B-Instruct](https://huggingface.co/tiiuae/falcon-40b-instruct), brainstorm ideas, discuss your holiday plans, and more!**
+
+                    ✨ This demo is powered by [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b), finetuned on the [Baize](https://github.com/project-baize/baize-chatbot) dataset. [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) is a state-of-the-art large language model built by the [Technology Innovation Institute](https://www.tii.ae) in Abu Dhabi. It is trained on 1 trillion tokens (including [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)) and available under the Apache 2.0 license. It currently holds the 🥇 1st place on the [🤗 Open LLM leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
+
+                    🧪 This is only a **first experimental preview**: we intend to provide increasingly capable versions of Falcon Chat in the future, based on improved datasets and RLHF/RLAIF.
+
+                    👀 **Learn more about Falcon LLM:** [falconllm.tii.ae](https://falconllm.tii.ae/)
+
+                    ➡️️ **Intended Use**: this demo is intended to showcase an early finetuning of [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b), to illustrate the impact (and limitations) of finetuning on a dataset of conversations and instructions. We encourage the community to further build upon the base model, and to create even better instruct/chat versions!
+
+                    ⚠️ **Limitations**: the model can and will produce factually incorrect information, hallucinating facts and actions. As it has not undergone any advanced tuning/alignment, it can produce problematic outputs, especially if prompted to do so. Finally, this demo is limited to a session length of about 1,000 words.
+                    """
+                )
+
+        chat(client)
+
+    return demo
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser("Playground Demo")
+    parser.add_argument(
+        "--addr",
+        type=str,
+        required=False,
+        default=INFERENCE_ENDPOINT,
+    )
+    args = parser.parse_args()
+    client = Client(args.addr, headers={"Authorization": f"Basic {INFERENCE_AUTH}"})
+    demo = get_demo(client)
+    demo.queue(max_size=128, concurrency_count=16)
+    demo.launch()