update

app.py

@@ -1,65 +1,49 @@
 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")
-client = InferenceClient("forestav/lora_model")
-
-
-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
-"""
+from llama_cpp import Llama
+from huggingface_hub import hf_hub_download
+
+def load_model():
+    # Download the model from HuggingFace
+    repo_id = "forestav/gguf_lora_model"
+    model_file = "unsloth.F16.gguf"  
+    
+    local_path = hf_hub_download(
+        repo_id=repo_id,
+        filename=model_file
+    )
+    
+    # Initialize the model
+    model = Llama(
+        model_path=local_path,
+        n_ctx=2048,
+        n_threads=8
+    )
+    
+    return model
+
+def generate_response(message, history):
+    # Generate response
+    response = model.create_chat_completion(
+        messages=[
+            {"role": "user", "content": message}
+        ],
+        max_tokens=512,
+        temperature=0.7,
+        top_p=0.95,
+    )
+    
+    return response['choices'][0]['message']['content']
+
+# Load model globally
+model = load_model()
+
+# Create Gradio interface with updated parameters
 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.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)",
-        ),
-    ],
+    fn=generate_response,
+    title="Your GGUF Model Chat",
+    description="A conversational AI model using GGUF format",
+    examples=["Continue the fibonacci sequence: 1, 1, 2, 3, 5, 8,"]
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

packages.txt

@@ -0,0 +1 @@
+build-essential

requirements.txt

@@ -1,3 +1,3 @@
 huggingface_hub==0.25.2
 gradio
-unsloth
+llama-cpp-python