changes

app.py

@@ -1,12 +1,24 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from llama_cpp import Llama
+from huggingface_hub import hf_hub_download
 
-"""
-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")
+# Define a function to load the model from the Hugging Face Hub
+def load_model():
+    repo_id = "forestav/gguf_lora_model"  # Your Hugging Face repo
+    model_file = "unsloth.F16.gguf"  # Model file in GGUF format
 
+    # Download the model file
+    local_path = hf_hub_download(repo_id=repo_id, filename=model_file)
+    print(f"Model loaded from: {local_path}")
 
+    # Load the model using llama_cpp
+    model = Llama(model_path=local_path, n_ctx=2048, n_threads=8, use_metal=False)
+    return model
+
+# Initialize the model
+model = load_model()
+
+# Define the response function for chat interaction
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -15,34 +27,34 @@ def respond(
     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]})
+    try:
+        # Prepare the system message and chat history
+        messages = [{"role": "system", "content": system_message}]
 
-    messages.append({"role": "user", "content": message})
+        # Add the history of the conversation
+        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 = ""
+        # Add the current message from the user
+        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
+        # Make the model prediction
+        response = model.create_chat_completion(
+            messages=messages,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+        )
+        return response["choices"][0]["message"]["content"]
 
-        response += token
-        yield response
+    except Exception as e:
+        # Return error message if something goes wrong
+        return f"Error: {e}"
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Define the Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -59,6 +71,6 @@ demo = gr.ChatInterface(
     ],
 )
 
-
+# Launch the app
 if __name__ == "__main__":
     demo.launch()

requirements.txt

@@ -1 +1,2 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+llama-cpp-python