Update app.py

app.py

@@ -1,48 +1,64 @@
 import gradio as gr
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig, LlamaConfig
-from peft import PeftModel  # For loading adapter files
-
-# Path to the base model and adapter
-BASE_MODEL_PATH = "unsloth/Llama-3.2-3B-Instruct"  # Replace with your base model path
-ADAPTER_PATH = "Futuresony/future_ai_12_10_2024.gguf"  # Your Hugging Face repo
-
-# Function to clean invalid rope_scaling fields in model config
-def clean_rope_scaling(config):
-    if "rope_scaling" in config:
-        rope_scaling = config["rope_scaling"]
-        # Retain only "type" and "factor" fields
-        config["rope_scaling"] = {
-            "type": rope_scaling.get("rope_type", "linear"),
-            "factor": rope_scaling.get("factor", 1.0),
-        }
-    return config
-
-# Load base model and tokenizer
-print("Loading base model and tokenizer...")
-tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL_PATH)
-
-# Load and clean model configuration
-config = LlamaConfig.from_pretrained(BASE_MODEL_PATH)
-cleaned_config_dict = clean_rope_scaling(config.to_dict())
-
-# Reconstruct the cleaned LlamaConfig object
-config = LlamaConfig(**cleaned_config_dict)
-
-# Load model with cleaned configuration
-print("Loading model...")
-model = AutoModelForCausalLM.from_pretrained(
-    BASE_MODEL_PATH, 
-    config=config, 
-    torch_dtype=torch.float16, 
-    device_map="auto"
-)
+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("Futuresony/future_ai_12_10_2024.gguf")
+
+
+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})
 
-# Load adapter using PEFT
-print("Loading adapter...")
-model = PeftModel.from_pretrained(model, ADAPTER_PATH)
+    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)",
+        ),
+    ],
+)
 
-# Set model to evaluation mode
-model.eval()
 
-print("Model and adapter loaded successfully!")
+if __name__ == "__main__":
+    demo.launch()