Add application file

app.py

@@ -0,0 +1,53 @@
+import gradio as gr
+import numpy as np
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+
+labels = {
+    0 : "Incorrect",
+    1 : "Partialy correct/Incomplete",
+    2 : "correct"
+}
+
+print('currently loading model')
+model = AutoModelForSequenceClassification.from_pretrained("./model")
+tokenizer = AutoTokenizer.from_pretrained("./tokenizer")
+print('model loaded successfully')
+
+def grade(model_answer, student_answer):
+    inputs = tokenizer(model_answer, student_answer, padding="max_length", truncation=True, return_tensors="pt")
+
+    with torch.no_grad():
+        logits = model(**inputs).logits
+    
+    preds = torch.nn.functional.softmax(logits, dim=1)
+    preds = np.concatenate(preds.numpy()).ravel().tolist()
+    print(preds)
+    return {l:p for p, l in zip(preds, labels.values())}
+
+demo = gr.Interface(
+    fn=grade, 
+    inputs=[
+        gr.Textbox(lines=2, placeholder="Model answer here"), 
+        gr.Textbox(lines=2, placeholder="Student answer here")
+    ], 
+    outputs="label",
+    title="Grading short answer questions",
+    examples=[
+        [
+            "A prototype is used to simulate the behavior of portions of the desired software product", 
+            "a prototype is used to simulate the behavior of a portion of the desired software product"
+        ],
+        [
+            "A variable in programming is a location in memory that can be used  to store a value", 
+            "no answer"
+        ],
+        [
+            "A computer system consists of a CPU, Memory, Input, and output devices.", 
+            "a CPU only"
+        ],
+    ],
+)
+
+demo.launch() 

model/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1eb7422279f59247275a5dd509c1463cc71e82922887e26aee34b4d32bdfbb5
+size 438008181

tokenizer/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}