Changes in app.py

app.py

@@ -1,25 +1,142 @@
+from threading import Thread
+from typing import Iterator
+
 import gradio as gr
-import os
+import spaces
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+
+DEFAULT_SYSTEM_PROMPT = "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."
+MAX_MAX_NEW_TOKENS = 2048
+DEFAULT_MAX_NEW_TOKENS = 1024
+MAX_INPUT_TOKEN_LENGTH = 4096
+
+DESCRIPTION = """\
+# Llama-2 7B Chat
+This Space demonstrates model [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta, a Llama 2 model with 7B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
+🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
+🔨 Looking for an even more powerful model? Check out the [13B version](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat) or the large [70B model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
+"""
+
+LICENSE = """
+<p/>
+---
+As a derivate work of [Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat) by Meta,
+this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat/blob/main/USE_POLICY.md).
+"""
+
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+
+
+if torch.cuda.is_available():
+    model_id = "meta-llama/Llama-2-7b-chat-hf"
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    tokenizer.use_default_system_prompt = False
+
+
+@spaces.GPU
+def generate(
+    message: str,
+    chat_history: list[tuple[str, str]],
+    system_prompt: str,
+    max_new_tokens: int = 1024,
+    temperature: float = 0.6,
+    top_p: float = 0.9,
+    top_k: int = 50,
+    repetition_penalty: float = 1.2,
+) -> Iterator[str]:
+    conversation = []
+    if system_prompt:
+        conversation.append({"role": "system", "content": system_prompt})
+    for user, assistant in chat_history:
+        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
+    conversation.append({"role": "user", "content": message})
+
+    chat = tokenizer.apply_chat_template(conversation, tokenize=False)
+    inputs = tokenizer(chat, return_tensors="pt", add_special_tokens=False).to("cuda")
+    if len(inputs) > MAX_INPUT_TOKEN_LENGTH:
+        inputs = inputs[-MAX_INPUT_TOKEN_LENGTH:]
+        gr.Warning("Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
 
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        inputs,
+        streamer=streamer,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
+        top_p=top_p,
+        top_k=top_k,
+        temperature=temperature,
+        num_beams=1,
+        repetition_penalty=repetition_penalty,
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
 
-model = "meta-llama/Llama-2-13b-chat-hf"
+    outputs = []
+    for text in streamer:
+        outputs.append(text)
+        yield "".join(outputs)
 
-API_URL = os.environ.get("API_URL")
-BEARER_TOKEN = os.environ.get("BEARER_TOKEN")
-import requests
 
-headers = {"Authorization": BEARER_TOKEN }
+chat_interface = gr.ChatInterface(
+    fn=generate,
+    additional_inputs=[
+        gr.Textbox(label="System prompt", value=DEFAULT_SYSTEM_PROMPT, lines=6),
+        gr.Slider(
+            label="Max new tokens",
+            minimum=1,
+            maximum=MAX_MAX_NEW_TOKENS,
+            step=1,
+            value=DEFAULT_MAX_NEW_TOKENS,
+        ),
+        gr.Slider(
+            label="Temperature",
+            minimum=0.1,
+            maximum=4.0,
+            step=0.1,
+            value=0.6,
+        ),
+        gr.Slider(
+            label="Top-p (nucleus sampling)",
+            minimum=0.05,
+            maximum=1.0,
+            step=0.05,
+            value=0.9,
+        ),
+        gr.Slider(
+            label="Top-k",
+            minimum=1,
+            maximum=1000,
+            step=1,
+            value=50,
+        ),
+        gr.Slider(
+            label="Repetition penalty",
+            minimum=1.0,
+            maximum=2.0,
+            step=0.05,
+            value=1.2,
+        ),
+    ],
+    stop_btn=None,
+    examples=[
+        ["Hello there! How are you doing?"],
+        ["Can you explain briefly to me what is the Python programming language?"],
+        ["Explain the plot of Cinderella in a sentence."],
+        ["How many hours does it take a man to eat a Helicopter?"],
+        ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
+    ],
+)
 
-def query(payload):
-	response = requests.post(API_URL, headers=headers, json=payload)
-	return response.json()
-	
-# output = query({
-# 	"inputs": "Can you please let us know more details about your ",
-# })
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
+    chat_interface.render()
+    gr.Markdown(LICENSE)
 
-def greet(name):
-    return "Hello " + name + "!!"
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch()
 
-iface = gr.Interface(fn=query, inputs="text", outputs="text")
-iface.launch(share=True)

requirements.txt

@@ -1,2 +1,9 @@
-gradio
-requests
+accelerate==0.23.0
+bitsandbytes==0.41.1
+gradio==3.47.1
+protobuf==3.20.3
+scipy==1.11.2
+sentencepiece==0.1.99
+spaces==0.16.1
+torch==2.0.0
+transformers==4.34.0

style.css

@@ -0,0 +1,16 @@
+h1 {
+    text-align: center;
+  }
+  
+  #duplicate-button {
+    margin: auto;
+    color: white;
+    background: #1565c0;
+    border-radius: 100vh;
+  }
+  
+  .contain {
+    max-width: 900px;
+    margin: auto;
+    padding-top: 1.5rem;
+  }