test

app.py

@@ -1,58 +1,120 @@
-import time
+from transformers import AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM
+from peft import PeftModel, PeftConfig
+import torch
+import gradio as gr
+import random
+from textwrap import wrap
+
+
+# Functions to Wrap the Prompt Correctly
+def wrap_text(text, width=90):
+    lines = text.split('\n')
+    wrapped_lines = [textwrap.fill(line, width=width) for line in lines]
+    wrapped_text = '\n'.join(wrapped_lines)
+    return wrapped_text
+
+
+def multimodal_prompt(user_input, system_prompt="You are an expert medical analyst:"):
+    """
+    Generates text using a large language model, given a user input and a system prompt.
+    Args:
+        user_input: The user's input text to generate a response for.
+        system_prompt: Optional system prompt.
+    Returns:
+        A string containing the generated text.
+    """
+    # Combine user input and system prompt
+    formatted_input = f"<s>[INST]{system_prompt} {user_input}[/INST]"
+
+    # Encode the input text
+    encodeds = tokenizer(formatted_input, return_tensors="pt", add_special_tokens=False)
+    model_inputs = encodeds.to(device)
+
+    # Generate a response using the model
+    output = model.generate(
+        **model_inputs,
+        max_length=max_length,
+        use_cache=True,
+        early_stopping=True,
+        bos_token_id=model.config.bos_token_id,
+        eos_token_id=model.config.eos_token_id,
+        pad_token_id=model.config.eos_token_id,
+        temperature=0.1,
+        do_sample=True
+    )
 
-from theme_dropdown import create_theme_dropdown  # noqa: F401
+    # Decode the response
+    response_text = tokenizer.decode(output[0], skip_special_tokens=True)
 
-import gradio as gr
+    return response_text
 
-dropdown, js = create_theme_dropdown()
 
-with gr.Blocks(theme='pseudolab/huggingface-korea-theme') as demo:
-    with gr.Row():
-        with gr.Column(scale=10):
-            gr.Markdown(
-                """
-                thank you for dong wook
-                """
-            )
+# Define the device
+device = "cuda" if torch.cuda.is_available() else "cpu"
 
+# Use the base model's ID
+base_model_id = "mistralai/Mistral-7B-v0.1"
+model_directory = "Tonic/mistralmed"
 
-    dropdown.change(None, dropdown, None, _js=js)
+# Instantiate the Tokenizer
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1", trust_remote_code=True, padding_side="left")
+# tokenizer = AutoTokenizer.from_pretrained("Tonic/mistralmed", trust_remote_code=True, padding_side="left")
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.padding_side = 'left'
 
+# Specify the configuration class for the model
+# model_config = AutoConfig.from_pretrained(base_model_id)
 
-    name = gr.Textbox(
-        label="Name",
-        info="Full name, including middle name. No special characters.",
-        placeholder="Jini77",
-        value="Jini77",
-        interactive=True,
-    )
+# Load the PEFT model with the specified configuration
+# peft_model = AutoModelForCausalLM.from_pretrained(base_model_id, config=model_config)
+
+# Load the PEFT model
+peft_config = PeftConfig.from_pretrained("Tonic/mistralmed", token="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")
+peft_model = MistralForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", trust_remote_code=True)
+peft_model = PeftModel.from_pretrained(peft_model, "Tonic/mistralmed", token="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")
+
+
+class ChatBot:
+    def __init__(self):
+        self.history = []
+
+
+class ChatBot:
+    def __init__(self):
+        # Initialize the ChatBot class with an empty history
+        self.history = []
+
+    def predict(self, user_input, system_prompt="You are an expert medical analyst:"):
+        # Combine the user's input with the system prompt
+        formatted_input = f"<s>[INST]{system_prompt} {user_input}[/INST]"
+
+        # Encode the formatted input using the tokenizer
+        user_input_ids = tokenizer.encode(formatted_input, return_tensors="pt")
 
+        # Generate a response using the PEFT model
+        response = peft_model.generate(input_ids=user_input_ids, max_length=512, pad_token_id=tokenizer.eos_token_id)
 
-    def go(*args):
-        time.sleep(3)
-        return "https://huggingface.co/spaces/pseudolab/interviewer_chat/blob/main/hugging-face-korea.png"
+        # Decode the generated response to text
+        response_text = tokenizer.decode(response[0], skip_special_tokens=True)
 
-    def clear():
-        time.sleep(0.2)
-        return None
+        return response_text  # Return the generated response
 
-    with gr.Row():
-        with gr.Column(scale=2):
-            chatbot = gr.Chatbot([("Hello", "Hi")], label="Chatbot")
-            chat_btn = gr.Button("Add messages")
 
-            def chat(history):
-                time.sleep(2)
-                yield [["How are you?", "I am good."]]
+bot = ChatBot()
 
-            chat_btn.click(
-                lambda history: history
-                + [["How are you?", "I am good."]]
-                + (time.sleep(2) or []),
-                chatbot,
-                chatbot,
-            )
+title = "자소서기반 면접 시뮬레이션 chat bot (this template based on Tonic's MistralMed Chat)"
+#description = "이 공간을 사용하여 현재 모델을 테스트할 수 있습니다. [(Tonic/MistralMed)](https://huggingface.co/Tonic/MistralMed) 또는 이 공간을 복제하고 로컬 또는 🤗HuggingFace에서 사용할 수 있습니다. [Discord에서 함께 만들기 위해 Discord에 가입하십시오](https://discord.gg/VqTxc76K3u). You can use this Space to test out the current model [(Tonic/MistralMed)](https://huggingface.co/Tonic/MistralMed) or duplicate this Space and use it locally or on 🤗HuggingFace. [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
+#examples = [["[Question:] What is the proper treatment for buccal herpes?",
+#             "You are a medicine and public health expert, you will receive a question, answer the question, and provide a complete answer"]]
 
+iface = gr.Interface(
+    fn=bot.predict,
+    title=title,
+    description=description,
+    examples=examples,
+    inputs=["text", "text"],  # Take user input and system prompt separately
+    outputs="text",
+    theme="ParityError/Anime"
+)
 
-if __name__ == "__main__":
-    demo.queue().launch()
+iface.launch()

theme_dropdown.py

@@ -1,57 +0,0 @@
-import os
-import pathlib
-
-from gradio.themes.utils import ThemeAsset
-
-
-def create_theme_dropdown():
-    import gradio as gr
-
-    asset_path = pathlib.Path(__file__).parent / "themes"
-    themes = []
-    for theme_asset in os.listdir(str(asset_path)):
-        themes.append(
-            (ThemeAsset(theme_asset), gr.Theme.load(str(asset_path / theme_asset)))
-        )
-
-    def make_else_if(theme_asset):
-        return f"""
-        else if (theme == '{str(theme_asset[0].version)}') {{
-            var theme_css = `{theme_asset[1]._get_theme_css()}`
-        }}"""
-
-    head, tail = themes[0], themes[1:]
-    if_statement = f"""
-        if (theme == "{str(head[0].version)}") {{
-            var theme_css = `{head[1]._get_theme_css()}`
-        }} {" ".join(make_else_if(t) for t in tail)}
-    """
-
-    latest_to_oldest = sorted([t[0] for t in themes], key=lambda asset: asset.version)[
-        ::-1
-    ]
-    latest_to_oldest = [str(t.version) for t in latest_to_oldest]
-
-    component = gr.Dropdown(
-        choices=latest_to_oldest,
-        value=latest_to_oldest[0],
-        render=False,
-        label="Select Version",
-    )
-
-    return (
-        component,
-        f"""
-        (theme) => {{
-            if (!document.querySelector('.theme-css')) {{
-                var theme_elem = document.createElement('style');
-                theme_elem.classList.add('theme-css');
-                document.head.appendChild(theme_elem);
-            }} else {{
-                var theme_elem = document.querySelector('.theme-css');
-            }}
-            {if_statement}
-            theme_elem.innerHTML = theme_css;
-        }}
-    """,
-    )