Duplicate from tiiuae/falcon-180b-demo

Co-authored-by: Falcon LLM TII UAE <FalconLLM@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,10 @@
+---
+title: Falcon-180B Demo
+emoji: 💬
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: 3.42.0
+app_file: app.py
+duplicated_from: tiiuae/falcon-180b-demo
+---

app.py

@@ -0,0 +1,145 @@
+import json
+import os
+import shutil
+import requests
+
+import gradio as gr
+from huggingface_hub import Repository, InferenceClient
+
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
+API_URL = "https://api-inference.huggingface.co/models/tiiuae/falcon-180B-chat"
+BOT_NAME = "Falcon"
+
+STOP_SEQUENCES = ["\nUser:", "<|endoftext|>", " User:", "###"]
+
+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 release of our latest AI model, Falcon LLM?"]
+    ]
+
+client = InferenceClient(
+    API_URL,
+    headers={"Authorization": f"Bearer {HF_TOKEN}"},
+)
+
+def format_prompt(message, history, system_prompt):
+  prompt = ""
+  if system_prompt:
+    prompt += f"System: {system_prompt}\n"
+  for user_prompt, bot_response in history:
+    prompt += f"User: {user_prompt}\n"
+    prompt += f"Falcon: {bot_response}\n" # Response already contains "Falcon: "
+  prompt += f"""User: {message}
+Falcon:"""
+  return prompt
+
+seed = 42
+
+def generate(
+    prompt, history, system_prompt="", temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
+):
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
+    global seed
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        stop_sequences=STOP_SEQUENCES,
+        do_sample=True,
+        seed=seed,
+    )
+    seed = seed + 1
+    formatted_prompt = format_prompt(prompt, history, system_prompt)
+
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+
+        for stop_str in STOP_SEQUENCES:
+            if output.endswith(stop_str):
+                output = output[:-len(stop_str)]
+                output = output.rstrip()
+                yield output
+        yield output
+    return output
+
+
+additional_inputs=[
+    gr.Textbox("", label="Optional system prompt"),
+    gr.Slider(
+        label="Temperature",
+        value=0.9,
+        minimum=0.0,
+        maximum=1.0,
+        step=0.05,
+        interactive=True,
+        info="Higher values produce more diverse outputs",
+    ),
+    gr.Slider(
+        label="Max new tokens",
+        value=256,
+        minimum=0,
+        maximum=8192,
+        step=64,
+        interactive=True,
+        info="The maximum numbers of new tokens",
+    ),
+    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",
+    ),
+    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.Blocks() as demo:
+    with gr.Row():
+        with gr.Column(scale=0.4):
+            gr.Image("better_banner.jpeg", elem_id="banner-image", show_label=False)
+        with gr.Column():
+            gr.Markdown(
+                """# Falcon-180B Demo
+
+                **Chat with [Falcon-180B-Chat](https://huggingface.co/tiiuae/falcon-180b-chat), brainstorm ideas, discuss your holiday plans, and more!**
+                
+                ✨ This demo is powered by [Falcon-180B](https://huggingface.co/tiiuae/falcon-180B) and finetuned on a mixture of [Ultrachat](https://huggingface.co/datasets/stingning/ultrachat), [Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus) and [Airoboros](https://huggingface.co/datasets/jondurbin/airoboros-2.1). [Falcon-180B](https://huggingface.co/tiiuae/falcon-180b) 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 3.5 trillion tokens (including [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)) and available under the [Falcon-180B TII License](https://huggingface.co/spaces/tiiuae/falcon-180b-license/blob/main/LICENSE.txt). It currently holds the 🥇 1st place on the [🤗 Open LLM leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) for a pretrained model. 
+                
+                🧪 This is only a **first experimental preview**: we intend to provide increasingly capable versions of Falcon 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-180B](https://huggingface.co/tiiuae/falcon-180b), 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.
+                """
+            )
+
+    gr.ChatInterface(
+        generate, 
+        examples=EXAMPLES,
+        additional_inputs=additional_inputs,
+    ) 
+
+demo.queue(concurrency_count=100, api_open=False).launch(show_api=False)

requirements.txt

@@ -0,0 +1,3 @@
+huggingface_hub
+gradio==3.42.0
+text-generation==0.4.1