Merge branch 'main' of https://huggingface.co/facebook/genre-large-kilt into main
Browse files
README.md
CHANGED
|
@@ -42,12 +42,12 @@ This model was trained on the full training set of [KILT](https://arxiv.org/abs/
|
|
| 42 |
Here is an example of generation for Wikipedia page retrieval for open-domain fact-checking:
|
| 43 |
|
| 44 |
```python
|
| 45 |
-
import pickle
|
| 46 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
| 47 |
|
| 48 |
# OPTIONAL: load the prefix tree (trie), you need to additionally download
|
| 49 |
# https://huggingface.co/facebook/genre-kilt/blob/main/trie.py and
|
| 50 |
# https://huggingface.co/facebook/genre-kilt/blob/main/kilt_titles_trie_dict.pkl
|
|
|
|
| 51 |
# from trie import Trie
|
| 52 |
# with open("kilt_titles_trie_dict.pkl", "rb") as f:
|
| 53 |
# trie = Trie.load_from_dict(pickle.load(f))
|
|
|
|
| 42 |
Here is an example of generation for Wikipedia page retrieval for open-domain fact-checking:
|
| 43 |
|
| 44 |
```python
|
|
|
|
| 45 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
| 46 |
|
| 47 |
# OPTIONAL: load the prefix tree (trie), you need to additionally download
|
| 48 |
# https://huggingface.co/facebook/genre-kilt/blob/main/trie.py and
|
| 49 |
# https://huggingface.co/facebook/genre-kilt/blob/main/kilt_titles_trie_dict.pkl
|
| 50 |
+
# import pickle
|
| 51 |
# from trie import Trie
|
| 52 |
# with open("kilt_titles_trie_dict.pkl", "rb") as f:
|
| 53 |
# trie = Trie.load_from_dict(pickle.load(f))
|