initial commit

README.md

@@ -1,3 +1,57 @@
+# Indonesia Recipe Ingredients Generator Model
+
+😎 *Have fun on generating ingredients* 😎
+
+This is a fine-tuned model to generate the Indonesian food ingredients. One of my personal project that I did in my free time.
+
+Basically, you give the name of the food and it will produce the ingredients of the food.
+
+## Model
+
+Data: [Indonesian Recipe Data on Kaggle](https://www.kaggle.com/datasets/canggih/indonesian-food-recipes)
+Pre-trained Model: [IndoBART-v2](https://huggingface.co/indobenchmark/indobart-v2)
+
+## How to use
+
+We will specify the use of the tokenizer and the model.
+
+### Tokenizer
+
+Since we use `indobart-v2`, we need to use their tokenizer.
+
+First, install the tokenizer using `pip install indobenchmark-toolkit`. 
+
+After that, you can load the tokenizer:
+
+```python
+from indobenchmark.tokenization_indonlg import IndoNLGTokenizer
+
+tokenizer = IndoNLGTokenizer.from_pretrained("haryoaw/id-recigen-bart")
+```
+
+### Model
+
+The model can be loaded by using AutoModel.
+
+```python
+from transformers import AutoModelWithLMHead
+
+model = AutoModelWithLMHead.from_pretrained("haryoaw/id-recigen-bart")
+```
+
+
+## Example of input
+
+```
+sayur asam
+```
+
+```
+nasi goreng ayam
+```
+
+~To be continued
+
 ---
 license: mit
 ---

added_tokens.json

@@ -0,0 +1 @@
+{"[java]": 40004, "[sunda]": 40005, "[indonesia]": 40006}

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "indobenchmark/indobart-v2",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "tokenizer_class": "IndoNLGTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 40004
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41feaa6591f0dd254c9fc51cbc94ba87e173ee0cdea1b7232c6107a54a4b4c0a
+size 526426993

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5508d2b2cf0a4a436783109db228742d2c8a1a70d94e3623a168e2b2b76b9cdf
+size 931715

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["[java]", "[sunda]", "[indonesia]", "<mask>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["[java]", "[sunda]", "[indonesia]", "<mask>"], "model_max_length": 768, "special_tokens_map_file": "C:\\Users\\62852/.cache\\huggingface\\transformers\\926850b94af761a8e24968d04fc4a1cf7b49a5f2f729eb1e9eca9adb10f8e623.d1720ecf2a739704b6f50fd1a86f320a93102bdf215b7e9f5450e0e35e897c41", "name_or_path": "indobenchmark/indobart-v2", "tokenizer_class": "IndoNLGTokenizer"}