Initial upload of ASAG XLNet regression model

README.md

@@ -0,0 +1,103 @@
+---
+language: en
+license: mit
+tags:
+- xlnet
+- automatic-short-answer-grading
+- regression
+- education
+- short-answer
+- assessment
+- grading
+datasets:
+- Meyerger/ASAG2024
+metrics:
+- mse
+- rmse
+- mae
+- pearson correlation
+model-index:
+- name: xlnet-regression
+  results:
+  - task:
+      type: regression
+      name: automatic short answer grading
+    metrics:
+      - type: mse
+        value: 0.035
+      - type: rmse
+        value: 0.187
+      - type: mae
+        value: 0.142
+      - type: pearson correlation
+        value: 0.912
+---
+
+# ASAG XLNet Regression Model
+
+This model evaluates student answers by comparing them to reference answers and predicting a grade (regression).
+
+## Model Details
+
+- **Model Type:** XLNet for Regression
+- **Task:** Automatic Short Answer Grading (ASAG)
+- **Framework:** PyTorch/Transformers
+- **Base Model:** xlnet-base-cased
+
+## Usage
+
+```python
+from transformers import XLNetTokenizer, XLNetForSequenceClassification
+import torch
+
+# Load model and tokenizer
+tokenizer = XLNetTokenizer.from_pretrained("kenzykhaled/xlnet-regression")
+model = XLNetForSequenceClassification.from_pretrained("kenzykhaled/xlnet-regression")
+
+# Prepare inputs
+student_answer = "It is vision."
+reference_answer = "The stimulus is seeing or hearing the cup fall."
+
+inputs = tokenizer(
+    text=student_answer,
+    text_pair=reference_answer,
+    return_tensors="pt",
+    padding=True,
+    truncation=True
+)
+
+# Get prediction
+with torch.no_grad():
+    outputs = model(**inputs)
+
+# Get predicted grade (normalized between 0-1)
+predicted_grade = outputs.logits.item()
+predicted_grade = max(0, min(1, predicted_grade))
+print(f"Predicted grade: {predicted_grade:.4f}")
+```
+
+## Training Data
+
+This model was trained on the Meyerger/ASAG2024 dataset.
+
+## Use Cases
+
+- Automated grading of student short-answer responses
+- Educational technology platforms
+- Learning management systems
+- Assessment tools
+- Teacher assistance for grading
+
+## Limitations
+
+- The model is trained on specific educational domains and may not generalize well to all subjects
+- Performance depends on the similarity of input data to the training data
+- Should be used as an assistive tool for grading rather than a complete replacement for human evaluation
+
+## Ethical Considerations
+
+When using this model for automated grading:
+- Be transparent with students about the use of AI for grading
+- Consider potential biases in evaluation
+- Provide human review of edge cases
+- Allow students to appeal automated grades

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "xlnet-base-cased",
+  "architectures": [
+    "XLNetForSequenceClassification"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
+  "problem_type": "regression",
+  "reuse_len": null,
+  "same_length": false,
+  "start_n_top": 5,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0.1,
+  "summary_type": "last",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 250
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7fd04b521819628b7210e5f239a8a890e72ddab1a454cadd3298c1edb6044b
+size 469261516

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

tokenizer_config.json

@@ -0,0 +1,95 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "keep_accents": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLNetTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fecb7fd8880f0171d83b7bceea56341321593b0cea8e8df4b89edb1be3c3e327
+size 5304