Update app.py

app.py

@@ -1,63 +1,63 @@
 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)",
-        ),
+from unsloth import FastLanguageModel
+from transformers import TextStreamer
+import torch
+
+# Function to load the model
+def load_model(model_name, max_seq_length, dtype, load_in_4bit, token=None):
+    model, tokenizer = FastLanguageModel.from_pretrained(
+        model_name=model_name,
+        max_seq_length=max_seq_length,
+        dtype=dtype,
+        load_in_4bit=load_in_4bit,
+        token=token
+    )
+    FastLanguageModel.for_inference(model)  # Enable native 2x faster inference
+    return model, tokenizer
+
+# Load the model
+model_name = "unsloth/Phi-3-mini-4k-instruct"
+token = None  # Replace with your token if required
+
+model, tokenizer = load_model(model_name, max_seq_length=2048, dtype=None, load_in_4bit=True, token=token)
+
+def generate_response(instruction, input_text, max_new_tokens):
+    alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
+
+    ### Instruction:
+    {}
+
+    ### Input:
+    {}
+
+    ### Response:
+    {}"""
+
+    inputs = tokenizer(
+        [
+            alpaca_prompt.format(
+                instruction,  # instruction
+                input_text,   # input
+                ""            # output - leave this blank for generation!
+            )
+        ], return_tensors="pt").to("cuda")
+
+    text_streamer = TextStreamer(tokenizer)
+    output = model.generate(**inputs, streamer=text_streamer, max_new_tokens=max_new_tokens)
+
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
+
+# Gradio Interface
+iface = gr.Interface(
+    fn=generate_response,
+    inputs=[
+        gr.Textbox(lines=2, label="Instruction", placeholder="Continue the Fibonacci sequence."),
+        gr.Textbox(lines=2, label="Input", placeholder="1, 1, 2, 3, 5, 8"),
+        gr.Slider(1, 2048, value=128, step=1, label="Max New Tokens")
     ],
+    outputs=gr.Textbox(label="Response", lines=10),
+    title="Language Model Chat UI"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()