Update app.py

app.py

@@ -1,63 +1,44 @@
-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(model="Rohan5manza/sentiment_analysis")
-
-
-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 financial advisor.", 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 transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+from unsloth import FastLanguageModel
+import torch
+
+
+max_seq_length = 4096 # Choose any! We auto support RoPE Scaling internally!
+dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
+load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
+
+# 4bit pre quantized models we support for 4x faster downloading + no OOMs.
+fourbit_models = [
+    "unsloth/llama-3-8b-Instruct-bnb-4bit",
+            ] 
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "unsloth/llama-3-8b-Instruct-bnb-4bit",
+    max_seq_length = max_seq_length,
+    dtype = dtype,
+    load_in_4bit = load_in_4bit,
+    # token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf
 )
 
 
-if __name__ == "__main__":
-    demo.launch()
+# Load the base model and apply LoRA adapters
+from transformers import AutoModel
+adapter_model = AutoModel.from_pretrained("Rohan5manza/sentiment_analysis")
+
+model = PeftModel.from_pretrained(model, adapter_model)
+
+def generate_response(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Example Gradio or Streamlit interface for deploying
+import gradio as gr
+
+def gradio_interface(prompt):
+    response = generate_response(prompt)
+    return response
+
+iface = gr.Interface(fn=gradio_interface, inputs="text", outputs="text")
+iface.launch()