Update app.py

app.py

@@ -1,63 +1,39 @@
 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,
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x22B-v0.1")
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x22B-v0.1", device_map="auto")
+
+# Function to generate text using the model
+def generate_text(prompt, max_length=500, temperature=0.7, top_k=50, top_p=0.95, num_return_sequences=1):
+    input_ids = tokenizer.encode(prompt, return_tensors="pt")
+    output = model.generate(
+        input_ids,
+        max_length=max_length,
         temperature=temperature,
+        top_k=top_k,
         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)",
-        ),
+        num_return_sequences=num_return_sequences,
+    )
+    generated_text = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
+    return generated_text
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.inputs.Textbox(lines=5, label="Input Prompt"),
+        gr.inputs.Slider(minimum=100, maximum=1000, default=500, step=50, label="Max Length"),
+        gr.inputs.Slider(minimum=0.1, maximum=1.0, default=0.7, step=0.1, label="Temperature"),
+        gr.inputs.Slider(minimum=1, maximum=100, default=50, step=1, label="Top K"),
+        gr.inputs.Slider(minimum=0.1, maximum=1.0, default=0.95, step=0.05, label="Top P"),
+        gr.inputs.Slider(minimum=1, maximum=10, default=1, step=1, label="Num Return Sequences"),
     ],
+    outputs=gr.outputs.Textbox(label="Generated Text"),
+    title="MixTRAL 8x22B Text Generation",
+    description="Use this interface to generate text using the MixTRAL 8x22B language model.",
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio interface
+iface.launch()