Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# 🧠 Lao Summarization Model - Fine-tuned Gemma 3 4B IT
|
| 2 |
|
| 3 |
This is a **Lao language summarization model** fine-tuned on the [`Phonepadith/laos_word_dataset`](https://huggingface.co/datasets/Phonepadith/laos_word_dataset), using the base model [`google/gemma-3-4b-it`](https://huggingface.co/google/gemma-3-4b-it). The model is designed to generate concise summaries from Lao language text.
|
|
@@ -28,6 +41,7 @@ This is a **Lao language summarization model** fine-tuned on the [`Phonepadith/l
|
|
| 28 |
You can load and use the model with Hugging Face Transformers and `adapter-transformers`:
|
| 29 |
|
| 30 |
```python
|
|
|
|
| 31 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 32 |
|
| 33 |
model_id = "Phonepadith/lao-gemma-summarizer" # change to your actual model name
|
|
@@ -39,4 +53,4 @@ inputs = tokenizer(input_text, return_tensors="pt")
|
|
| 39 |
summary_ids = model.generate(**inputs, max_new_tokens=100)
|
| 40 |
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
|
| 41 |
|
| 42 |
-
print(summary)
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- Phonepadith/laos_word_dataset
|
| 5 |
+
language:
|
| 6 |
+
- lo
|
| 7 |
+
metrics:
|
| 8 |
+
- bleu
|
| 9 |
+
base_model:
|
| 10 |
+
- google/gemma-3-4b-it
|
| 11 |
+
pipeline_tag: summarization
|
| 12 |
+
library_name: fastai
|
| 13 |
+
---
|
| 14 |
# 🧠 Lao Summarization Model - Fine-tuned Gemma 3 4B IT
|
| 15 |
|
| 16 |
This is a **Lao language summarization model** fine-tuned on the [`Phonepadith/laos_word_dataset`](https://huggingface.co/datasets/Phonepadith/laos_word_dataset), using the base model [`google/gemma-3-4b-it`](https://huggingface.co/google/gemma-3-4b-it). The model is designed to generate concise summaries from Lao language text.
|
|
|
|
| 41 |
You can load and use the model with Hugging Face Transformers and `adapter-transformers`:
|
| 42 |
|
| 43 |
```python
|
| 44 |
+
|
| 45 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 46 |
|
| 47 |
model_id = "Phonepadith/lao-gemma-summarizer" # change to your actual model name
|
|
|
|
| 53 |
summary_ids = model.generate(**inputs, max_new_tokens=100)
|
| 54 |
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
|
| 55 |
|
| 56 |
+
print(summary)
|