Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
language:
|
| 3 |
- sa
|
| 4 |
- en
|
|
@@ -7,6 +8,7 @@ tags:
|
|
| 7 |
- vocabulary-expansion
|
| 8 |
- low-resource
|
| 9 |
- lora
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# gemma2-2b-sa-1k-0
|
|
@@ -41,9 +43,18 @@ outputs = model.generate(**inputs, max_new_tokens=100)
|
|
| 41 |
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 42 |
```
|
| 43 |
|
| 44 |
-
##
|
| 45 |
|
| 46 |
```bibtex
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
### CC-100 (Training Data)
|
| 48 |
|
| 49 |
@inproceedings{conneau-etal-2020-unsupervised,
|
|
|
|
| 1 |
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
language:
|
| 4 |
- sa
|
| 5 |
- en
|
|
|
|
| 8 |
- vocabulary-expansion
|
| 9 |
- low-resource
|
| 10 |
- lora
|
| 11 |
+
base_model: google/gemma-2-2b
|
| 12 |
---
|
| 13 |
|
| 14 |
# gemma2-2b-sa-1k-0
|
|
|
|
| 43 |
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 44 |
```
|
| 45 |
|
| 46 |
+
## Citations
|
| 47 |
|
| 48 |
```bibtex
|
| 49 |
+
### Gemma 2 (Base Model)
|
| 50 |
+
|
| 51 |
+
@article{gemma2024,
|
| 52 |
+
title = "Gemma 2: Improving Open Language Models at a Practical Size",
|
| 53 |
+
author = "{Gemma Team, Google DeepMind}",
|
| 54 |
+
journal = "arXiv preprint arXiv:2408.00118",
|
| 55 |
+
year = "2024",
|
| 56 |
+
url = "https://arxiv.org/abs/2408.00118",
|
| 57 |
+
}
|
| 58 |
### CC-100 (Training Data)
|
| 59 |
|
| 60 |
@inproceedings{conneau-etal-2020-unsupervised,
|