init inference

app.py

@@ -1,11 +1,10 @@
 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("Mat17892/llama_lora_G14")
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
+# Load your model and tokenizer
+model_name = "Mat17892/llama_lora_model_1"  # Replace with your Hugging Face model name
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
 def respond(
     message,
@@ -15,47 +14,40 @@ def respond(
     temperature,
     top_p,
 ):
-    # Combine the system message and chat history into a single string
-    prompt = system_message + "\n"
-    for user_input, assistant_reply in history:
-        if user_input:
-            prompt += f"User: {user_input}\n"
-        if assistant_reply:
-            prompt += f"Assistant: {assistant_reply}\n"
-    prompt += f"User: {message}\nAssistant:"
+    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]})
 
-    # Send the request to the model
-    response = ""
-    for token in client.text_generation(
-        prompt,
-        max_new_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        response += token.token
-        yield response
+    messages.append({"role": "user", "content": message})
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+    # Prepare input for the model
+    input_text = message
+    inputs = tokenizer(input_text, return_tensors="pt")
+    
+    # Generate response
+    outputs = model.generate(
+        **inputs, 
+        max_new_tokens=max_tokens, 
+        temperature=temperature, 
+        top_p=top_p
+    )
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Create the Gradio interface
 demo = gr.ChatInterface(
     respond,
-    type="messages",
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"),
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()