Update space

.gitignore

@@ -0,0 +1,2 @@
+*.venv
+*.gitattributes

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "taipyStudio.gUI.elementsFilePaths": []
+}

app.py

@@ -1,50 +1,60 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+class Assistant:
+    def __init__(self, model_name="ContactDoctor/Bio-Medical-Llama-3-8B"):
+            self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+            self.model = AutoModelForCausalLM.from_pretrained(model_name)
+            self.pipe = pipeline("text-generation", model="ContactDoctor/Bio-Medical-Llama-3-8B")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    def respond(
+        self,
+        message,
+        history: list[tuple[str, str]],
+        system_message,
+        max_tokens,
+        temperature,
+        top_p,
+    ):
+        messages = [{"role": "system", "content": system_message}]
 
-    messages.append({"role": "user", "content": message})
+        for val in history:
+            if val[0]:
+                messages.append({"role": "user", "content": val[0]})
+            if val[1]:
+                messages.append({"role": "assistant", "content": val[1]})
 
-    response = ""
+        messages.append({"role": "user", "content": message})
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        response = ""
 
-        response += token
-        yield response
+        for message in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = message.choices[0].delta.content
+
+            response += token
+            yield response
 
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
+assistant = Assistant()
+
 demo = gr.ChatInterface(
-    respond,
+    assistant.respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
@@ -61,4 +71,5 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
+    # Assistant()
     demo.launch()