Update app.py

app.py

@@ -1,67 +1,34 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
 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("deepseek-ai/deepseek-llm-7b-base")
-# Use a pipeline as a high-level helper
-#from transformers import pipeline
-
-#pipe = pipeline("text-generation", model="deepseek-ai/deepseek-llm-7b-base")
-
-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)",
-        ),
-    ],
+# Load the model and tokenizer
+model_name = "deepseek-ai/deepseek-llm-7b-base"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
+model.generation_config = GenerationConfig.from_pretrained(model_name)
+model.generation_config.pad_token_id = model.generation_config.eos_token_id
+
+def generate_response(prompt):
+    # Tokenize the input prompt
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    
+    # Generate the response
+    outputs = model.generate(**inputs, max_new_tokens=100)
+    
+    # Decode the generated tokens to a string
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    
+    return response
+
+# Create a Gradio interface
+iface = gr.Interface(
+    fn=generate_response,  # Function to call
+    inputs="text",         # Input type
+    outputs="text",        # Output type
+    title="DeepSeek 7B Chat",  # Title of the app
+    description="A simple chat interface for the DeepSeek 7B model."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the app
+iface.launch()