testing deployment

app.py

@@ -1,65 +1,47 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel, PeftConfig
 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("Alkhalaf/test")
-
-
-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)",
-        ),
-    ],
+from huggingface_hub import login
+import torch
+import os
+hf_token = os.getenv("llama")
+login(hf_token)
+# Model and adapter paths
+model_name = "unsloth/llama-3.2-1b-instruct-bnb-4bit"  # Base model
+adapter_name = "Alkhalaf/lora_model"  # LoRA model adapter
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
+
+# Load the LoRA adapter configuration
+peft_config = PeftConfig.from_pretrained(adapter_name, use_auth_token=True)
+
+# Load the base model
+base_model = AutoModelForCausalLM.from_pretrained(
+    peft_config.base_model_name_or_path,
+   
+    #torch_dtype=torch.float16
+
+    
+)
+# Apply the LoRA adapter to the base model
+model = PeftModel.from_pretrained(base_model, adapter_name, use_auth_token=True)
+
+# Define prediction function
+def predict(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt")
+    outputs = model.generate(inputs["input_ids"], max_length=150)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=predict,
+    inputs="text",
+    outputs="text",
+    title="Conversational AI with LoRA",
+    description="Interact with a fine-tuned LoRA model for conversational AI."
 )
-
 
 if __name__ == "__main__":
-    demo.launch()
+    interface.launch(share=True)