Update app.py

app.py

@@ -1,64 +1,46 @@
 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("IsmaelMousa/SmolLM2-135M-Instruct-EngSaf-217K")
-
-
-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 grading assistant. Evaluate student answers based on the mark scheme. Respond only in JSON format with keys 'score' (int) and 'rationale' (string).", 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 transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import torch
+
+checkpoint = "IsmaelMousa/SmolLM2-135M-Instruct-EngSaf-217K"
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
+assistant = pipeline("text-generation", tokenizer=tokenizer, model=model, device=0 if torch.cuda.is_available() else -1)
+
+def grade(question, reference_answer, student_answer, mark_scheme, max_tokens, temperature, top_p):
+    system_content = "You are a grading assistant. Evaluate student answers based on the mark scheme. Respond only in JSON format with keys \"score\" (int) and \"rationale\" (string)."
+    
+    user_content = (
+        "Provide both a score and a rationale by evaluating the student's answer strictly within the mark scheme range, "
+        "grading based on how well it meets the question's requirements by comparing the student answer to the reference answer.\n"
+        f"Question: {question}\n"
+        f"Reference Answer: {reference_answer}\n"
+        f"Student Answer: {student_answer}\n"
+        f"Mark Scheme: {mark_scheme}"
+    )
+    
+    messages = [{"role": "system", "content": system_content}, {"role": "user", "content": user_content}]
+    inputs = tokenizer.apply_chat_template(messages, tokenize=False)
+    
+    output = assistant(inputs, max_new_tokens=max_tokens, do_sample=True, temperature=temperature, top_p=top_p, return_full_text=False)[0]["generated_text"]
+    
+    return output
+
+demo = gr.Interface(
+    fn=grade,
+    inputs=[
+        gr.Textbox(label="Question"),
+        gr.Textbox(label="Reference Answer"),
+        gr.Textbox(label="Student Answer"),
+        gr.Textbox(label="Mark Scheme"),
+        gr.Slider(minimum=1, maximum=512, value=128, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, 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"),
     ],
+    outputs=gr.Textbox(label="Evaluation Output (JSON)")
 )
 
-
 if __name__ == "__main__":
     demo.launch()