Update app.py

change model to llama3

app.py

@@ -1,63 +1,58 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-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]})
-
-    messages.append({"role": "user", "content": message})
-
-    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
-"""
-demo = gr.ChatInterface(
-    respond,
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+import os 
+
+model_name = "meta-llama/Meta-Llama-3-8B-Instruct"
+device_map = 'cuda'
+
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
+
+def load_model() -> AutoModelForCausalLM:
+    return AutoModelForCausalLM.from_pretrained(model_name, device_map=device_map)
+
+def load_tokenizer() -> AutoTokenizer:
+    return AutoTokenizer.from_pretrained(model_name)
+
+def preprocess_messages(message: str, history: list, system_prompt: str) -> dict:
+    messages = [{'role': 'system', 'content': system_prompt}, {'role': 'user', 'content': message}]
+    prompt = load_tokenizer().apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    return prompt
+
+def generate_text(prompt: str, max_new_tokens: int, temperature: float) -> str:
+    model = load_model()
+    terminators = [load_tokenizer().eos_token_id, load_tokenizer().convert_tokens_to_ids(['\n'])]
+    temp = temperature + 0.1
+    outputs = model.generate(
+        prompt,
+        max_new_tokens=max_new_tokens,
+        eos_token_id=terminators[0],
+        do_sample=True,
+        temperature=temp,
+        top_p=0.9
+     )
+    return load_tokenizer().decode(outputs[0], skip_special_tokens=True)
+
+def chat_function(
+    message: str,
+    history: list,
+    system_prompt: str,
+    max_new_tokens: int,
+    temperature: float
+) -> str:
+    prompt = preprocess_messages(message, history, system_prompt)
+    return generate_text(prompt, max_new_tokens, temperature)
+
+gr.ChatInterface(
+    chat_function,
+    chatbot=gr.Chatbot(height=400),
+    textbox=gr.Textbox(placeholder="Enter message here", container=False, scale=7),
+    title="LLAMA3 Chat",
+    description="""Chat with llama3""",
+    theme="soft",
     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"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+        gr.Textbox("You shall answer to all the questions as very smart AI", label="System Prompt"),
+        gr.Slider(512, 4096, label="Max New Tokens"),
+        gr.Slider(0, 1, label="Temperature")
+     ]
+).launch(debug=True)