Update README.md
Browse files
README.md
CHANGED
|
@@ -12,10 +12,7 @@ base_model:
|
|
| 12 |
pipeline_tag: translation
|
| 13 |
---
|
| 14 |
|
| 15 |
-
#
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
# Sea Lion Taglish Translation Model
|
| 19 |
|
| 20 |
## Model Summary
|
| 21 |
|
|
@@ -33,6 +30,19 @@ This model is intended for research, experimentation, and development of machine
|
|
| 33 |
|
| 34 |
**Not recommended** for high-stakes or formal use cases such as medical, legal, or governmental translation.
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
## How to Use
|
| 37 |
|
| 38 |
```python
|
|
@@ -46,19 +56,9 @@ inputs = tokenizer(prompt, return_tensors="pt")
|
|
| 46 |
output = model.generate(**inputs, max_new_tokens=100)
|
| 47 |
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
| 48 |
|
| 49 |
-
|
| 50 |
-
- **Developed by:** Charlotte Puopolo
|
| 51 |
-
- **Model type:** Machine Translation trained on English-Taglish parallel Tweets
|
| 52 |
-
- **Language(s) (NLP):** Taglish (English-Tagalog code-switching)
|
| 53 |
-
- **License:** [More Information Needed]
|
| 54 |
-
- **Finetuned from model [optional]:** Tweet Taglish dataset (Herrera et al., 2022)
|
| 55 |
-
|
| 56 |
-
### Model Sources
|
| 57 |
-
|
| 58 |
-
- **Repository:** https://github.com/puopolo/Taglish-Translation/tree/main/prompts
|
| 59 |
-
- **Paper:** [Coming soon]
|
| 60 |
-
|
| 61 |
```
|
|
|
|
|
|
|
| 62 |
If you use this model, please cite:
|
| 63 |
|
| 64 |
@misc{puopolo2025taglish,
|
|
|
|
| 12 |
pipeline_tag: translation
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# Sea-Lion Taglish Translation Model
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model Summary
|
| 18 |
|
|
|
|
| 30 |
|
| 31 |
**Not recommended** for high-stakes or formal use cases such as medical, legal, or governmental translation.
|
| 32 |
|
| 33 |
+
## Model Specs
|
| 34 |
+
|
| 35 |
+
- **Developed by:** Charlotte Puopolo
|
| 36 |
+
- **Model type:** Machine Translation trained on English-Taglish parallel Tweets
|
| 37 |
+
- **Language(s) (NLP):** Taglish (English-Tagalog code-switching)
|
| 38 |
+
- **License:** [More Information Needed]
|
| 39 |
+
- **Finetuned from model [optional]:** Tweet Taglish dataset (Herrera et al., 2022)
|
| 40 |
+
|
| 41 |
+
### Model Sources
|
| 42 |
+
|
| 43 |
+
- **Repository:** https://github.com/puopolo/Taglish-Translation/tree/main/prompts
|
| 44 |
+
- **Paper:** [Coming soon]
|
| 45 |
+
-
|
| 46 |
## How to Use
|
| 47 |
|
| 48 |
```python
|
|
|
|
| 56 |
output = model.generate(**inputs, max_new_tokens=100)
|
| 57 |
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
| 58 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
```
|
| 60 |
+
|
| 61 |
+
## How to Cite
|
| 62 |
If you use this model, please cite:
|
| 63 |
|
| 64 |
@misc{puopolo2025taglish,
|