Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- flan-t5
|
| 4 |
+
- essay-scoring
|
| 5 |
+
- education
|
| 6 |
+
- grading
|
| 7 |
+
- gpt-evaluation
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
language:
|
| 10 |
+
- en
|
| 11 |
+
pipeline_tag: text2text-generation
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# flan-t5-base-pt2 — Essay Trait Scorer
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of `google/flan-t5-base` designed for trait-based essay scoring. It was trained on Sets 7 & 8 of the ASAP AES dataset, extended with floating-point scoring and GPT validation.
|
| 17 |
+
|
| 18 |
+
Each input includes:
|
| 19 |
+
- a trait (e.g., Ideas, Organization),
|
| 20 |
+
- the relevant rubric definition,
|
| 21 |
+
- and the student's essay.
|
| 22 |
+
|
| 23 |
+
The model outputs a trait-specific score between **0.0 and 3.0**, which can be scaled to a final grade out of 100.
|
| 24 |
+
|
| 25 |
+
🧠 Scoring is optionally cross-validated with OpenAI’s GPT for more reliable results.
|
| 26 |
+
|
| 27 |
+
## Usage
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
| 31 |
+
|
| 32 |
+
tokenizer = AutoTokenizer.from_pretrained("srutiii/flan-t5-base-pt2")
|
| 33 |
+
model = AutoModelForSeq2SeqLM.from_pretrained("srutiii/flan-t5-base-pt2")
|
| 34 |
+
|