Update app.py

app.py

@@ -1,63 +1,161 @@
+import spaces
+import json
+import subprocess
+from llama_cpp import Llama
+from llama_cpp_agent import LlamaCppAgent, MessagesFormatterType
+from llama_cpp_agent.providers import LlamaCppPythonProvider
+from llama_cpp_agent.chat_history import BasicChatHistory
+from llama_cpp_agent.chat_history.messages import Roles
 import gradio as gr
-from huggingface_hub import InferenceClient
+from huggingface_hub import hf_hub_download
+
+hf_hub_download(
+    repo_id="bartowski/gemma-2-9b-it-GGUF",
+    filename="gemma-2-9b-it-Q5_K_M.gguf",
+    local_dir="./models"
+)
+
+
+
+hf_hub_download(
+    repo_id="bartowski/gemma-2-27b-it-GGUF",
+    filename="gemma-2-27b-it-Q5_K_M.gguf",
+    local_dir="./models"
+)
 
-"""
-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")
 
+llm = None
+llm_model = None
 
+@spaces.GPU(duration=120)
 def respond(
     message,
     history: list[tuple[str, str]],
+    model,
     system_message,
     max_tokens,
     temperature,
     top_p,
+    top_k,
+    repeat_penalty,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    chat_template = MessagesFormatterType.GEMMA_2
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    global llm
+    global llm_model
+    
+    if llm is None or llm_model != model:
+        llm = Llama(
+            model_path=f"models/{model}",
+            flash_attn=True,
+            n_gpu_layers=81,
+            n_batch=1024,
+            n_ctx=8192,
+        )
+        llm_model = model
 
-    messages.append({"role": "user", "content": message})
+    provider = LlamaCppPythonProvider(llm)
 
-    response = ""
+    agent = LlamaCppAgent(
+        provider,
+        system_prompt=f"{system_message}",
+        predefined_messages_formatter_type=chat_template,
+        debug_output=True
+    )
+    
+    settings = provider.get_provider_default_settings()
+    settings.temperature = temperature
+    settings.top_k = top_k
+    settings.top_p = top_p
+    settings.max_tokens = max_tokens
+    settings.repeat_penalty = repeat_penalty
+    settings.stream = True
 
-    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
+    messages = BasicChatHistory()
 
-        response += token
-        yield response
+    for msn in history:
+        user = {
+            'role': Roles.user,
+            'content': msn[0]
+        }
+        assistant = {
+            'role': Roles.assistant,
+            'content': msn[1]
+        }
+        messages.add_message(user)
+        messages.add_message(assistant)
+    
+    stream = agent.get_chat_response(
+        message,
+        llm_sampling_settings=settings,
+        chat_history=messages,
+        returns_streaming_generator=True,
+        print_output=False
+    )
+    
+    outputs = ""
+    for output in stream:
+        outputs += output
+        yield outputs
 
+description = """<p align="center"><a href="https://huggingface.co/spaces/gokaygokay/Gemma-2-llamacpp" target="_blank">[Reference Space]</a></p>
+<p><center>
+<p align="center">Defaults to 27B it (you can switch to 9b it from additional inputs)</p>
+<p><center>
+<a href="https://huggingface.co/google/gemma-2-27b-it" target="_blank">[27B it Model]</a>
+<a href="https://huggingface.co/google/gemma-2-9b-it" target="_blank">[9B it Model]</a>
+<a href="https://huggingface.co/bartowski/gemma-2-27b-it-GGUF" target="_blank">[27B it Model GGUF]</a>
+<a href="https://huggingface.co/bartowski/gemma-2-9b-it-GGUF" target="_blank">[9B it Model GGUF]</a>
+</center></p>
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+
 demo = gr.ChatInterface(
     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"),
+        gr.Dropdown([
+                'gemma-2-9b-it-Q5_K_M.gguf',
+                'gemma-2-27b-it-Q5_K_M.gguf'
+            ],
+            value="gemma-2-27b-it-Q5_K_M.gguf",
+            label="Model"
+        ),
+        gr.Textbox(value="You are a helpful assistant.", label="System message"),
+        gr.Slider(minimum=1, maximum=4096, value=2048, step=1, label="Max 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)",
+            label="Top-p",
+        ),
+        gr.Slider(
+            minimum=0,
+            maximum=100,
+            value=40,
+            step=1,
+            label="Top-k",
+        ),
+        gr.Slider(
+            minimum=0.0,
+            maximum=2.0,
+            value=1.1,
+            step=0.1,
+            label="Repetition penalty",
         ),
     ],
+    retry_btn="Retry",
+    undo_btn="Undo",
+    clear_btn="Clear",
+    submit_btn="Send",
+    title="Chat with Gemma 2 using llama.cpp", 
+    description=description,
+    chatbot=gr.Chatbot(
+        scale=1, 
+        likeable=False,
+        show_copy_button=True
+    )
 )
 
-
 if __name__ == "__main__":
     demo.launch()