Update space

app.py

@@ -1,70 +1,52 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
+# Load a small DeepSeek Coder model suitable for CPU and limited RAM usage
+model_name = "deepseek-ai/deepseek-coder-1.3b-base"  # Change to smaller model for your RAM if needed
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
 
-    messages = [{"role": "system", "content": system_message}]
+# Put model in eval mode (no training)
+model.eval()
 
-    messages.extend(history)
+def generate_code(prompt, max_tokens, temperature, top_p):
+    # Tokenize input prompt
+    inputs = tokenizer(prompt, return_tensors="pt")
 
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # Generate output tokens
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id,
+    )
 
-        response += token
-        yield response
+    # Decode generated tokens to string
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
+    # Return generated completion excluding the input prompt for clarity
+    return generated_text[len(prompt):].strip()
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
-
+# Gradio app interface
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
+    gr.Markdown("# DeepSeek Coder Chatbot")
+    prompt_input = gr.Textbox(label="Code Prompt", lines=5, placeholder="Write your code prompt here...")
+    max_tokens_slider = gr.Slider(1, 1024, value=512, step=1, label="Max Generated Tokens")
+    temperature_slider = gr.Slider(0.1, 1.0, value=0.7, step=0.05, label="Temperature")
+    top_p_slider = gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="Top-p (nucleus sampling)")
+    generate_btn = gr.Button("Generate Code")
+    output = gr.Textbox(label="Generated Code", lines=15)
+
+    generate_btn.click(
+        fn=generate_code,
+        inputs=[prompt_input, max_tokens_slider, temperature_slider, top_p_slider],
+        outputs=output,
+    )
 
 if __name__ == "__main__":
     demo.launch()