Update app.py

app.py

@@ -5,7 +5,8 @@ from typing import Iterator
 import gradio as gr
 import spaces
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer, BitsAndBytesConfig
+from peft import PeftModel
 
 MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
@@ -13,17 +14,13 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("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).
@@ -34,8 +31,14 @@ if not torch.cuda.is_available():
 
 
 if torch.cuda.is_available():
+    bnb_config = BitsAndBytesConfig(
+    load_in_8bit=True,
+    bnb_4bit_compute_dtype=torch.float16,
+    )
     model_id = "meta-llama/Llama-2-7b-chat-hf"
-    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
+    base_model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto",quantization_config=bnb_config)
+    model = PeftModel.from_pretrained(
+    base_model,"ranamhamoud/storytell")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False
 
@@ -44,7 +47,6 @@ if torch.cuda.is_available():
 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,
@@ -52,8 +54,6 @@ def generate(
     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})
@@ -85,61 +85,25 @@ def generate(
         yield "".join(outputs)
 
 
-# chat_interface = gr.ChatInterface(
-#     fn=generate,
-#     additional_inputs=[
-#         gr.Textbox(label="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'"],
-#     ],
-# )
+chat_interface = gr.ChatInterface(
+    fn=generate,
+    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'"],
+    ],
+)
 
 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()
+    chat_interface.render()
     gr.Markdown(LICENSE)
 
 if __name__ == "__main__":
     demo.queue(max_size=20).launch()
+
+