Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
This is a `distilgpt2` model, finetuned on the Wikitext-103 dataset.
|
2 |
+
|
3 |
+
It achieves a perplexity of **18.25** using a "sliding window" context, using the `run_clm.py` script at [https://github.com/neulab/knn-transformers](https://github.com/neulab/knn-transformers).
|
4 |
+
|
5 |
+
| Base LM: | `distilgpt2` | `gpt2` |
|
6 |
+
| :--- | ----: | ---: |
|
7 |
+
| base perplexity | 18.25 | 14.84 |
|
8 |
+
| + kNN-LM | 15.03 | 12.57 |
|
9 |
+
| + RetoMaton | **14.70** | **12.46** |
|
10 |
+
|
11 |
+
This model was released as part of the paper ["Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval"](https://arxiv.org/pdf/2201.12431.pdf) (ICML'2022).
|
12 |
+
For more information, see: [https://github.com/neulab/knn-transformers](https://github.com/neulab/knn-transformers)
|