Update app.py

app.py

@@ -1,64 +1,24 @@
-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,
-    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()
+import os
+from transformers import AutoModel, AutoTokenizer
+
+# Directory containing GGUF files
+gguf_directory = "/path/to/gguf/files"  # Replace with your actual directory path
+
+# Filter files containing 'Q2_K'
+def find_q2_k_models(directory):
+    return [file for file in os.listdir(directory) if "Q2_K" in file and file.endswith(".gguf")]
+
+# Load the appropriate model
+def load_q2_k_model(gguf_directory):
+    q2_k_files = find_q2_k_models(gguf_directory)
+    if not q2_k_files:
+        raise ValueError("No GGUF files with 'Q2_K' found in the specified directory.")
+    # Load the first matching file (or implement logic for user selection)
+    model_path = os.path.join(gguf_directory, q2_k_files[0])
+    print(f"Loading model from: {model_path}")
+    model = AutoModel.from_pretrained(model_path)
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+    return model, tokenizer
+
+# Initialize the model
+model, tokenizer = load_q2_k_model(gguf_directory)