Update README.md

README.md

@@ -1,32 +1,42 @@
----
-license: apache-2.0
-datasets:
-- Phonepadith/laos_word_dataset
-language:
-- lo
-metrics:
-- bleu
-base_model:
-- google/gemma-3-4b-it
-library_name: adapter-transformers
-pipeline_tag: summarization
+# 🧠 Lao Summarization Model - Fine-tuned Gemma 3 4B IT
+
+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.
+
 ---
 
+## 📌 Model Details
+
+- **Base Model**: [`google/gemma-3-4b-it`](https://huggingface.co/google/gemma-3-4b-it)
+- **Fine-tuned by**: [Phonepadith](https://huggingface.co/Phonepadith)
+- **Language**: Lao (`lo`)
+- **Task**: Summarization
+- **Dataset**: [`Phonepadith/laos_word_dataset`](https://huggingface.co/datasets/Phonepadith/laos_word_dataset)
+- **Library**: `adapter-transformers`
+- **License**: Apache 2.0
+
 ---
-### Detail Versions
-base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:unsloth/gemma-3-4b-it-unsloth-bnb-4bit
-- lora
-- sft
-- transformers
-- trl
-- unsloth
+
+## 📊 Metrics
+
+- **Evaluation Metric**: BLEU score  
+  BLEU is used to evaluate the quality of generated summaries against reference summaries in the dataset.
+
 ---
 
+## 🛠️ How to Use
+
+You can load and use the model with Hugging Face Transformers and `adapter-transformers`:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "Phonepadith/lao-gemma-summarizer"  # change to your actual model name
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
 
-### Framework versions
+input_text = "ຂໍ້ຄວາມຕົ້ນສະບັບທີ່ຈະໃຫ້ສະຫຼຸບ"
+inputs = tokenizer(input_text, return_tensors="pt")
+summary_ids = model.generate(**inputs, max_new_tokens=100)
+summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
 
-- PEFT 0.16.0
+print(summary)