Add dataset, prompt, and language information on README.md

README.md

@@ -2,9 +2,13 @@
 tags:
 - generated_from_trainer
 base_model: cahya/gpt2-large-indonesian-522M
+datasets:
+- cahya/alpaca-id-cleaned
 model-index:
 - name: my-random-gpt-ft-3
   results: []
+language:
+- id
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -12,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my-random-gpt-ft-3
 
-This model is a fine-tuned version of [cahya/gpt2-large-indonesian-522M](https://huggingface.co/cahya/gpt2-large-indonesian-522M) on an unknown dataset.
+This model is a fine-tuned version of [cahya/gpt2-large-indonesian-522M](https://huggingface.co/cahya/gpt2-large-indonesian-522M) on [cahya/alpaca-id-cleaned](https://huggingface.co/datasets/cahya/alpaca-id-cleaned) dataset.
 
 ## Model description
 
@@ -20,7 +24,14 @@ More information needed
 
 ## Intended uses & limitations
 
-More information needed
+Prompt format:
+```
+Pengguna: <insert user prompt here>
+
+Asisten:
+```
+
+Limitation: This model can't understand the prompt well enough.
 
 ## Training and evaluation data
 
@@ -48,4 +59,4 @@ The following hyperparameters were used during training:
 - Transformers 4.39.3
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.0
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2