Update app.py

app.py

@@ -1,63 +1,26 @@
 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("Qwen/Qwen2-7B-Instruct")
-
-
-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 the person telling the story. You add many details and you write angry.", label="System message", lines=7),
-        gr.Slider(minimum=1, maximum=10000, 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
+
+# Load the model and tokenizer
+model_name = "cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Define the prediction function
+def predict(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return generated_text
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your text here..."),
+    outputs="text",
+    title="Dolphin-2.9.3-Mistral-Nemo-12b Text Generation",
+    description="Generate text using the Dolphin-2.9.3-Mistral-Nemo-12b model from Hugging Face."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+iface.launch()